ICML 2025 Schedule

Filter Events

SUN 13 JUL

11 a.m.

Registration West

(ends 5:30 PM)

2 p.m.

Expo Talk Panel:

AutoML for Tabular, Graph, Time series, and Multi-modal Data: Democratizing AI Across Diverse Data Landscapes

(ends 3:00 PM)

Expo Talk Panel:

Gen AI Applications in Amazon Pharmacy

(ends 3:00 PM)

Expo Talk Panel:

OmniLong: A Resource-Effective Context Scaling Framework for Multimodal LLM Fine-tuning

(ends 3:00 PM)

Expo Talk Panel:

Thursday Night Football on Prime Video – Broadcast Innovation

(ends 3:00 PM)

3 p.m.

Break:

Coffee Break

(ends 4:00 PM)

4 p.m.

Expo Talk Panel:

A Unified Framework for Generative AI Safety

(ends 5:00 PM)

Expo Talk Panel:

Distributed Computing Architectures as a Solution to AI's Energy Crisis: Empirical Analysis of Decentralized Training

(ends 5:00 PM)

Expo Talk Panel:

JokeEval: Are the Jokes Funny? Review of Computational Evaluation Techniques to improve Joke Generation

(ends 5:00 PM)

5 p.m.

Expo Talk Panel:

Toward Stateless Training of LLMs: Breaking Memory Barriers Without Sacrificing Performance

(ends 6:00 PM)

Expo Talk Panel:

Re-Imagine: Symbolic Benchmark Synthesis for Reasoning Evaluation

(ends 6:00 PM)

Expo Talk Panel:

Distillation Scaling Laws

(ends 6:00 PM)

Expo Talk Panel:

Human-Aligned Long-Form Evaluation (HALF-Eval): Framework for Assessing AI-Generated Content

(ends 6:00 PM)

MON 14 JUL

7:30 a.m.

Registration West

(ends 6:00 PM)

ICML Lounge Area:

ICML Lounge Area

(ends 6:00 PM)

Registration East

(ends 3:00 PM)

8 a.m.

Affinity Workshop:

LatinX in AI

(ends 5:30 PM)

Affinity Workshop:

4th MusIML workshop at ICML’25

(ends 5:30 PM)

Expo Talk Panel:

Situating principles in context for synthetic data

(ends 9:00 AM)

Expo Talk Panel:

Otter: Generating Tests from Issues to Validate SWE Patches

(ends 9:00 AM)

Expo Talk Panel:

The Next Frontier in Enterprise AI: A Vision for Generalist Agents

(ends 9:00 AM)

Expo Talk Panel:

Improving LLM Benchmarks: Making AI Work for Real-World Needs

(ends 9:00 AM)

Expo Talk Panel:

Foundation Models for Automated Trading

(ends 9:00 AM)

9 a.m.

Break:

Coffee Break

(ends 10:00 AM)

9:30 a.m.

Tutorial:

Calibration and Bias in Algorithms, Data, and Models: a tutorial on metrics and plots for measuring calibration, bias, fairness, reliability, and robustness

(ends 12:00 PM)

Tutorial:

Modern Methods in Associative Memory

(ends 12:00 PM)

Tutorial:

Alignment Methods for Large Language Models

(ends 12:00 PM)

Tutorial:

Generative AI Meets Reinforcement Learning

(ends 12:00 PM)

Tutorial:

Harnessing Low Dimensionality in Diffusion Models: From Theory to Practice

(ends 12:00 PM)

Tutorial:

DP-fy your DATA: How to (and why) synthesize Differentially Private Synthetic Data

(ends 12:00 PM)

noon

Break:

Hosted Grab and Go Lunch

(ends 1:30 PM)

1:30 p.m.

Tutorial:

Game-theoretic Statistics and Sequential Anytime-Valid Inference

(ends 4:00 PM)

Tutorial:

Tutorial on Mechanistic Interpretability for Language Models

(ends 4:00 PM)

Tutorial:

Jailbreaking LLMs and Agentic Systems: Attacks, Defenses, and Evaluations

(ends 4:00 PM)

Tutorial:

Flowing Through Continuous-Time Generative Models: A Clear and Systematic Tour

(ends 4:00 PM)

Tutorial:

Training Neural Networks at Any Scale

(ends 4:00 PM)

Tutorial:

The Underlying Logic of Language Models

(ends 4:00 PM)

4 p.m.

Break:

Coffee Break

(ends 5:00 PM)

Exhibits

(ends 8:00 PM)

Expo Demonstration:

IBM software agent for code (ISAC)

(ends 8:00 PM)

Expo Demonstration:

Production Strength Sales Agent

(ends 8:00 PM)

Expo Demonstration:

Excitement-Driven AI Sports Commentary Generation

(ends 8:00 PM)

Expo Demonstration:

Building Advanced Software Engineering LLM Agents with Codellm-Devkit (CLDK)

(ends 8:00 PM)

Expo Demonstration:

WCA4Z Platform - Accelerating Legacy Code Modernization Using AI Agents, Deep Program Analysis, and Scalable AI Pipelines

(ends 8:00 PM)

Expo Demonstration:

Prompt Declaration Language (PDL)

(ends 8:00 PM)

Expo Demonstration:

Real-World Autonomy: Building Modular, Voice-Guided Embodied Agents with SLMs and Vision

(ends 8:00 PM)

Expo Demonstration:

Knobs of the Mind: Dopamine, Serotonin, and a Maze-Running Rover

(ends 8:00 PM)

4:30 p.m.

Expo Workshop:

AI in Finance: Innovation & Emerging Opportunities

(ends 6:00 PM)

Expo Workshop:

Uncertainty Estimation in LLM-Generated Content

(ends 6:00 PM)

Expo Workshop:

Evaluation of GenAI models

(ends 6:00 PM)

Expo Talk Panel:

Sidekick

(ends 5:30 PM)

Expo Talk Panel:

Graph Foundation Models: Thoughts and Results

(ends 6:00 PM)

6:30 p.m.

Reception:

Welcome Reception

(ends 8:00 PM)

TUE 15 JUL

7:30 a.m.

Registration West

(ends 6:00 PM)

ICML Lounge Area:

ICML Lounge Area

(ends 7:00 PM)

Registration East

(ends 12:00 PM)

8 a.m.

Affinity Workshop:

New In ML

(ends 5:30 PM)

8:30 a.m.

Invited Talk:

Invited Talk - Jon Kleinberg

Jon Kleinberg

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

Exhibits

(ends 6:00 PM)

10 a.m.

Oral 1A Alignment and Agents [10:00-11:00]

Orals 10:00-11:00

[10:00] Multi-agent Architecture Search via Agentic Supernet

[10:15] Training a Generally Curious Agent

[10:30] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

[10:45] CollabLLM: From Passive Responders to Active Collaborators

(ends 11:00 AM)

Oral 1B Positions: Better Ways to Do Machine Learning [10:00-11:00]

Orals 10:00-11:00

[10:00] Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards

[10:15] Position: A Critical Perspective on The Value in Studying Deep Learning Phenomena

[10:30] Position: Certified Robustness Does Not (Yet) Imply Model Security

[10:45] Position: Probabilistic Modelling is Sufficient for Causal Inference

(ends 11:00 AM)

Oral 1C Applications in Computer Vision [10:00-11:00]

Orals 10:00-11:00

[10:00] VideoRoPE: What Makes for Good Video Rotary Position Embedding?

[10:15] ReferSplat: Referring Segmentation in 3D Gaussian Splatting

[10:30] Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection

[10:45] VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

(ends 11:00 AM)

Oral 1D Learning Dynamics 1 [10:00-11:00]

Orals 10:00-11:00

[10:00] Algorithm Development in Neural Networks: Insights from the Streaming Parity Task

[10:15] Learning Dynamics in Continual Pre-Training for Large Language Models

[10:30] Strategy Coopetition Explains the Emergence and Transience of Emergent In-Context Learning

[10:45] Transformative or Conservative? Conservation laws for ResNets and Transformers

(ends 11:00 AM)

Oral 1E Theory and Phenomenology [10:00-11:00]

Orals 10:00-11:00

[10:00] An analytic theory of creativity in convolutional diffusion models

[10:15] Layer by Layer: Uncovering Hidden Representations in Language Models

[10:30] Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks

[10:45] Emergence in non-neural models: grokking modular arithmetic via average gradient outer product

(ends 11:00 AM)

11 a.m.

Poster Session 1 [11:00-1:30]

Posters 11:00-1:30

Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$

A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks

AMPO: Active Multi Preference Optimization

An Efficient Private GPT Never Autoregressively Decodes

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy

Contextual Online Decision Making with Infinite-Dimensional Functional Regression

Differential Privacy Under Class Imbalance: Methods and Empirical Insights

Does learning the right latent variables necessarily improve in-context learning?

Finding Information Quality: Counterfactual Voting Adjustment for Quality Assessment and Fairer Voting in Online Platforms with Helpfulness Evaluation

Fraud-Proof Revenue Division on Subscription Platforms

GaussMark: A Practical Approach for Structural Watermarking of Language Models

(How) Can Transformers Predict Pseudo-Random Numbers?

How to Move Your Dragon: Text-To-Motion Synthesis For Large-Vocabulary Objects

Improving the Variance of Differentially Private Randomized Experiments through Clustering

It's My Data Too: Private ML for Datasets with Multi-User Training Examples

Knowledge-Guided Wasserstein Distributionally Robust Optimization

LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations

Local Pan-privacy for Federated Analytics

Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning

Navigating Conflicting Views: Harnessing Trust For Learning

Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability

On the Learnability of Distribution Classes with Adaptive Adversaries

OR-Bench: An Over-Refusal Benchmark for Large Language Models

Prediction via Shapley Value Regression

Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction

R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

Scalably Solving Assistance Games

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models

Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances

Telling Peer Direct Effects from Indirect Effects in Observational Network Data

Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning

Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

The impact of on-policy parallelized data collection on network plasticity in deep reinforcement learning

Towards Learning to Complete Anything in Lidar

Training Consistency Models with Variational Noise Coupling

Uncertainty Quantification for LLM-Based Survey Simulations

Vision-Language Models Create Cross-Modal Task Representations

$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting

$Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma

A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment

A Closer Look at the Generalized BH Algorithm

A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features

Action-Constrained Imitation Learning

Active feature acquisition via explainability-driven ranking

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes

Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation

Adaptive Localization of Knowledge Negation for Continual LLM Unlearning

Adaptive Sample Sharing for Multi Agent Linear Bandits

Adaptive Self-improvement LLM Agentic System for ML Library Development

Ad-Hoc Human-AI Coordination Challenge

Adjustment for Confounding using Pre-Trained Representations

Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge

Adversarial Optimization of Multidimensional Adaptive Coefficients in Flow and Diffusion Models

Adversarial Perturbations Are Linear Combinations of the Right Singular Vectors of the Attack-Targets-Ranking Constrained Jacobian

A First-order Generative Bilevel Optimization Framework for Diffusion Models

A Free Lunch for Length Extrapolation in Video Diffusion Transformers

A General Framework for Inference-time Scaling and Steering of Diffusion Models

Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning

Aggregation Buffer: Revisiting DropEdge with a New Parameter Block

Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

A Hitchhiker's Guide to Scaling Law Estimation

AKORN: Adaptive Knots generated Online for RegressioN Splines

Algorithm Development in Neural Networks: Insights from the Streaming Parity Task

Aligning Multimodal Representations through an Information Bottleneck

Aligning Protein Conformation Ensemble Generation with Physical Feedback

All-Atom Inverse Folding Through Discrete Flow Matching

A machine learning approach to duality in statistical physics

A Mathematical Framework for AI-Human Integration in Work

A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models

An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures

Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction

An analytic theory of creativity in convolutional diffusion models

An Asymptotically Optimal Approximation Algorithm for Multiobjective Submodular Maximization at Scale

Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation

A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators

Approximation to Smooth Functions by Low-rank Swish Networks

Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation

A Reasoning-Based Approach to Cryptic Crossword Clue Solving

A Recipe for Causal Graph Regression: Confounding Effects Revisited

Are Foundation Models Foundational? Synthetic Tasks Reveal World Models

Arrow: Accelerator for Time Series Causal Discovery with Time Weaving

A Sample Efficient Conditional Independence Test in the Presence of Discretization

A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach

A shot of Cognac to forget bad memories: Corrective Unlearning in GNNs

A Simple Model of Inference Scaling Laws

A Stronger Mixture of Low-rank Experts for Fine-Tuning Foundation Models

A Sub-Problem Quantum Alternating Operator Ansatz for Correlation Clustering

Asymmetric Decision-Making in Online Knowledge Distillation: Unifying Consensus and Divergence

AtlasD: Automatic Local Symmetry Discovery

A Trichotomy for List Transductive Online Learning

Auditing Prompt Caching in Language Model APIs

Autoformulation of Mathematical Optimization Models Using LLMs

Automatic Differentiation of Optimization Algorithms with Time-Varying Updates

A Variational Perspective on Generative Protein Fitness Optimization

Average Sensitivity of Hierarchical $k$-Median Clustering

Avoiding spurious sharpness minimization broadens applicability of SAM

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality

Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach

Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling

Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment

Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation

Bifurcate then Alienate: Incomplete Multi-view Clustering via Coupled Distribution Learning with Linear Overhead

BILBO: BILevel Bayesian Optimization

Bi-perspective Splitting Defense: Achieving Clean-Data-Free Backdoor Security

Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?

Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Calibrated Value-Aware Model Learning with Probabilistic Environment Models

Calibrating Video Watch-time Predictions with Credible Prototype Alignment

CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

Causal Logistic Bandits with Counterfactual Fairness Constraint

Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention

CellFlow: Simulating Cellular Morphology Changes via Flow Matching

Clustering Items through Bandit Feedback: Finding the Right Feature out of Many

CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations

CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective

CollabLLM: From Passive Responders to Active Collaborators

CombiMOTS: Combinatorial Multi-Objective Tree Search For Dual-Target Molecule Generation

Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe method

Competing Bandits in Matching Markets via Super Stability

Compressed and distributed least-squares regression: convergence rates with applications to federated learning

Concept-Centric Token Interpretation for Vector-Quantized Generative Models

Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations

Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting

Confidence Difference Reflects Various Supervised Signals in Confidence-Difference Classification

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

Constrained Pareto Set Identification with Bandit Feedback

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Contextual Linear Bandits with Delay as Payoff

Contract Design Under Approximate Best Responses

Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization

CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution Diversity

COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation

CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering

Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making

CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning

Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects

Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects Models

Decoupled SGDA for Games with Intermittent Strategy Communication

Deep principal support vector machines for nonlinear sufficient dimension reduction

Deep Streaming View Clustering

Deep Unsupervised Hashing via External Guidance

Delta Decompression for MoE-based LLMs Compression

Detecting Strategic Deception with Linear Probes

DexSim: Automating Data Scaling for Sim2Real Generalizable Robot Control

Differentially Private Synthetic Image Generation with Few-Shot Data and Generative APIs

Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

Discrepancy Minimization in Input-Sparsity Time

Disentangling and Integrating Relational and Sensory Information in Transformer Architectures

Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms

Distinguishing Cause from Effect with Causal Velocity Models

Distributed Differentially Private Data Analytics via Secure Sketching

Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold

Diversifying Robot Locomotion Behaviors with Extrinsic Behavioral Curiosity

Divide and Conquer: Learning Label Distribution with Subtasks

Diving into Self-Evolve Training for Multimodal Reasoning

Do Bayesian Neural Networks Actually Behave Like Bayesian Models?

DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning

Do Multiple Instance Learning Models Transfer?

Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering

Doubly Protected Estimation for Survival Outcomes Utilizing External Controls for Randomized Clinical Trials

Doubly Robust Conformalized Survival Analysis with Right-Censored Data

Dynamic Sparse Training of Diagonally Sparse Networks

DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation

Editable Concept Bottleneck Models

Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity

Efficient and Scalable Reinforcement Learning for Average Reward under Model Uncertainty

Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

Efficient Motion Prompt Learning for Robust Visual Tracking

Efficient optimization with orthogonality constraint: a randomized Riemannian submanifold method

Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity

Efficient Personalized Adaption for Physiological Signal Foundation Model

Eigenspectrum Analysis of Weight Matrices without Aspect Ratio Bias

Emergence and Effectiveness of Task Vectors in In-Context Learning : An Encoder Decoder Perspective

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability

Ensemble Distribution Distillation via Flow Matching

Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems

EvalX: A Platform for Code LLM Evaluation in the Wild

Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts

Exploiting Curvature in Online Convex Optimization with Delayed Feedback

Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling

ExpProof : Operationalizing Explanations for Confidential Models with ZKPs

Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity

Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation

Faster Approximation Algorithms for k-Center via Data Reduction

Fast Estimation of Partial Dependence Functions using Trees

Fast inference with Kronecker-sparse matrices

FDGen: A Fairness-Aware Graph Generation Model

Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions

Feature out! Let Raw Image as Your Condition for Blind Face Restoration

Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework

FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning

FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts

FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks

Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness

Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape

Fleet of Agents: Coordinated Problem Solving with Large Language Models

FlexiClip: Locality-Preserving Free-Form Character Animation

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

Focus On This, Not That! Steering LLMs With Adaptive Feature Specification

Foundation Model Canonicalization: A Zero-Shot Path to Invariant Perception

Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization

From Language Models over Tokens to Language Models over Characters

From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection

From RAG to Memory: Non-Parametric Continual Learning for Large Language Models

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

Function-to-Style Guidance of LLMs for Code Translation

G-Adaptivity: optimised graph-based mesh relocation for finite element methods

Generalized Interpolating Discrete Diffusion

Generative Point Cloud Registration

Geometry-Informed Neural Networks

GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention

Global curvature for second-order optimization of neural networks

GMAIL: Generative Modality Alignment for generated Image Learning

Goal-Space Planning with Subgoal Models

GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code

Great Language Models Think Alike and this Undermines AI Oversight

Griffin: Towards a Graph-Centric Relational Database Foundation Model

GuidedQuant: Large Language Model Quantization via Exploiting End-to-End Loss Guidance

Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference

HashAttention: Semantic Sparsity for Faster Inference

HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion

High Dynamic Range Novel View Synthesis with Single Exposure

Homophily Enhanced Graph Domain Adaptation

How compositional generalization and creativity improve as diffusion models are trained

How Much Can We Forget about Data Contamination?

How to set AdamW's weight decay as you scale model and dataset size

How Useful are Your Jailbreak Outputs?

HPS: Hard Preference Sampling for Human Preference Alignment

HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder

Hyperbolic GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations

Identifying and Understanding Cross-Class Features in Adversarial Training

Identifying biological perturbation targets through causal differential networks

Identifying metric structures of deep latent variable models

iDPA: Instance Decoupled Prompt Attention for Continual Medical Object Detection

Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling

Improving Memory Efficiency for Training KANs via Meta Learning

Improving Parallel Program Performance with LLM Optimizers via Agent-System Interface

iN2V: Bringing Transductive Node Embeddings to Inductive Graphs

In-Context Learning as Conditioned Associative Memory Retrieval

In-Context Meta Learning Induces Multi-Phase Circuit Emergence

In-Context Reinforcement Learning From Suboptimal Historical Data

Incorporating Arbitrary Matrix Group Equivariance into KANs

Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization

InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference

Instance Correlation Graph-based Naive Bayes

Integration-free kernels for equivariant Gaussian process modelling

Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems

Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

Investigating the Overlooked Hessian Structure: From CNNs to LLMs

Isolated Causal Effects of Natural Language

Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization

KIND: Knowledge Integration and Diversion for Training Decomposable Models

KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference

Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models

LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation

Language Models over Canonical Byte-Pair Encodings

LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection

LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing

Large Displacement Motion Transfer with Unsupervised Anytime Interpolation

Large Language Models are Demonstration Pre-Selectors for Themselves

Large Language Models to Diffusion Finetuning

LASER: Attention with Exponential Transformation

Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing

Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data

Layer by Layer: Uncovering Hidden Representations in Language Models

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation

Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees

Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning

Learning curves theory for hierarchically compositional data with power-law distributed features

Learning Dynamics in Continual Pre-Training for Large Language Models

Learning Event Completeness for Weakly Supervised Video Anomaly Detection

Learning Extrapolative Sequence Transformations from Markov Chains

Learning Gaussian DAG Models without Condition Number Bounds

Learning Latent Graph Structures and their Uncertainty

Learning Monotonic Probabilities with a Generative Cost Model

Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Learning multivariate Gaussians with imperfect advice

Learning Optimal Multimodal Information Bottleneck Representations

Learning-Order Autoregressive Models with Application to Molecular Graph Generation

Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems

Learning to Keep a Promise: Teaching LLMs an Annotation Language for Asynchronous Decoding

Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Learning to Match Unpaired Data with Minimum Entropy Coupling

Learning to Quantize for Training Vector-Quantized Networks

Learning without Isolation: Pathway Protection for Continual Learning

Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective

Leveraging Randomness in Model and Data Partitioning for Privacy Amplification

LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Sparse Fine-Tuning

Lightweight-Mark: Rethinking Deep Learning-Based Watermarking

Lightweight Online Adaption for Time Series Foundation Model Forecasts

LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data

Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model

LoRA-Gen: Specializing Large Language Model via Online LoRA Generation

Masked Autoencoders Are Effective Tokenizers for Diffusion Models

Masked Generative Nested Transformers with Decode Time Scaling

MATS: An Audio Language Model under Text-only Supervision

Measuring Diversity in Synthetic Datasets

Mechanistic PDE Networks for Discovery of Governing Equations

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction

MIRROR: Make Your Multi-View Generation More Consistent with Training-Free Rectification

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

MixMin: Finding Data Mixtures via Convex Minimization

Model Uncertainty Quantification in Continual Learning

MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition

MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

MTSTRec: Multimodal Time-Aligned Shared Token Recommender

Multi-agent Architecture Search via Agentic Supernet

Multi-armed Bandits with Interference

Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points

Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning

Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks

Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration

Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback

Neural Collapse Beyond the Unconstrainted Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime

Neural Guided Diffusion Bridges

No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets

Nonparametric Teaching for Graph Property Learners

Not All Wrong is Bad: Using Adversarial Examples for Unlearning

Offline Learning for Combinatorial Multi-armed Bandits

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework for Diffusion Models

On Exact Bit-level Reversible Transformers Without Changing Architectures

On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding

On Learning Parallel Pancakes with Mostly Uniform Weights

Online Conformal Prediction via Online Optimization

Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning

Online Learning in the Random-Order Model

On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving

On the Impact of Performative Risk Minimization for Binary Random Variables

On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks

On the Power of Context-Enhanced Learning in LLMs

On the Statistic Mechanisms of Distributional Compositional Generalization

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?

Open Materials Generation with Stochastic Interpolants

Optimal Algorithm for Max-Min Fair Bandit

Optimal Transfer Learning for Missing Not-at-Random Matrix Completion

Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization

Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach

Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection

OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference

OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction

Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization

Pareto-frontier Entropy Search with Variational Lower Bound Maximization

Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model

PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations

PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction

Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive Querying

Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning

PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation

PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning

PINNsAgent: Automated PDE Surrogation with Large Language Models

PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization

PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models

Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models

Policy Filtration for RLHF to Mitigate Noise in Reward Models

Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints

Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications

Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems

Position: A Critical Perspective on The Value in Studying Deep Learning Phenomena

Position: AI Safety Must Embrace an Antifragile Perspective

Position: AI Scaling: From Up to Down and Out

Position: A Theory of Deep Learning Must Include Compositional Sparsity

Position: Certified Robustness Does Not (Yet) Imply Model Security

Position: Constants are Critical in Regret Bounds for Reinforcement Learning

Position: Future Research and Challenges Remain Towards AI for Software Engineering

Position: Language model developers should report train-test overlap

Position: Lifetime tuning is incompatible with continual reinforcement learning

Position: Probabilistic Modelling is Sufficient for Causal Inference

Position: Rethinking Explainable Machine Learning as Applied Statistics

Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives

Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived

Position: Supervised Classifiers Answer the Wrong Questions for OOD Detection

Position: The Categorization of Race in ML is a Flawed Premise

Practical and Near-Optimal Algorithm for Batched Linear Bandits

Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary Optimization

Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies

Preference Learning for AI Alignment: a Causal Perspective

Preference learning made easy: Everything should be understood through win rate

Pre-Memorization Train Accuracy Reliably Predicts Generalization in LLM Reasoning

Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG

Primal-Dual Neural Algorithmic Reasoning

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting

Privacy Amplification Through Synthetic Data: Insights from Linear Regression

Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models

Private Lossless Multiple Release

ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation

Provable In-Context Vector Arithmetic via Retrieving Task Concepts

QPRL : Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal

Quadratic Differentiable Optimization for the Maximum Independent Set Problem

Quadratic Upper Bound for Boosting Robustness

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models

Quantifying Treatment Effects: Estimating Risk Ratios via Observational Studies

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures

Random Registers for Cross-Domain Few-Shot Learning

RankNovo: A Universal Reranking Approach for Robust De Novo Peptide Sequencing

Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models

Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems

RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts

ReferSplat: Referring Segmentation in 3D Gaussian Splatting

Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens

Relational Invariant Learning for Robust Solvation Free Energy Prediction

Relative Error Fair Clustering in the Weak-Strong Oracle Model

Reliable Algorithm Selection for Machine Learning-Guided Design

Representation Preserving Multiclass Agnostic to Realizable Reduction

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions

Residual Matrix Transformers: Scaling the Size of the Residual Stream

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach

Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification

Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning

Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model

Revisiting Non-Acyclic GFlowNets in Discrete Environments

Revisiting Unbiased Implicit Variational Inference

Reviving the Cooperation Dynamics in Multimodal Transformer

Rhomboid Tiling clustering for geometric graph deep learning

Riemannian Diffusion Adaptation for Distributed Optimization on Manifolds

Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Robust and Conjugate Spatio-Temporal Gaussian Processes

Robust Off-Policy Actor-Critic: Virtual Alternative Training via Symmetric Policy Evaluation

Robust Reward Alignment via Hypothesis Space Batch Cutting

RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

SafeMap: Robust HD Map Construction from Incomplete Observations

Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics

SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation

Sargy: Targeted Human Feedback for LLM Alignment

Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks

Scaling Inference-Efficient Language Models

Scaling Laws for Floating–Point Quantization Training

Scaling Test-Time Compute Without Verification or RL is Suboptimal

Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning

SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields

Secant Line Search for Frank-Wolfe Algorithms

Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games

Selective Prompt Anchoring for Code Generation

Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning

Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator

Settling the Maximin Share Fairness for Scheduling among Groups of Machines

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

ShieldAgent: Shielding LLM Agents via Verifiable Safety Policy Reasoning

SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity & Hierarchy in Efficiently Layered Decoder

Signed Laplacians for Constrained Graph Clustering

Simple Path Structural Encoding for Graph Transformers

Solving Zero-Sum Convex Markov Games

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging

Sparse-pivot: Dynamic correlation clustering for node insertions

Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry

Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding

Spherical-Nested Diffusion Model for Panoramic Image Outpainting

Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models

Staged and Physics-Grounded Learning Framework with Hyperintensity Prior for Pre-Contrast MRI Synthesis

STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification

Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training

Strategy Coopetition Explains the Transience of Emergent In-Context Learning

SWIFTCODE: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning

Symmetry-Driven Discovery of Dynamical Variables in Molecular Simulations

Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion

Synthetic Text Generation for Training Large Language Models via Gradient Matching

TabFSBench: Tabular Benchmark for Feature Shifts in Open Environment

TAROT: Targeted Data Selection via Optimal Transport

Temperature-Annealed Boltzmann Generators

Tensor Product Neural Networks for Functional ANOVA Model

Testing the limits of fine-tuning to improve reasoning in vision language models

Test-Time Multimodal Backdoor Detection by Contrastive Prompting

Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data

The Batch Complexity of Bandit Pure Exploration

The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text

The Disparate Benefits of Deep Ensembles

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering

The impact of uncertainty on regularized learning in games

The Logical Implication Steering Method for Conditional Interventions on Transformer Generation

The Missing Alignment Link of In-context Learning on Sequences

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret

The Role of Sparsity for Length Generalization in LLMs

The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability

The Surprising Effectiveness of Test-Time Training for Few-Shot Learning

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data

The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training

Time-Aware World Model for Adaptive Prediction and Control

TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning

Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time

TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction

Tool Unlearning for Tool-Augmented LLMs

Topology-aware Neural Flux Prediction Guided by Physics

Toward Efficient Kernel-Based Solvers for Nonlinear PDEs

Towards Attributions of Input Variables in a Coalition

Towards a Unified Framework of Clustering-based Anomaly Detection

Towards Cost-Effective Reward Guided Text Generation

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models

Towards Robust Influence Functions with Flat Validation Minima

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis

Towards Universal Offline Black-Box Optimization via Learning String Embedding Space

Tracking Most Significant Shifts in Infinite-Armed Bandits

Tracking The Best Expert Privately

Training a Generally Curious Agent

Training Deep Learning Models with Norm-Constrained LMOs

Trajectory World Models for Heterogeneous Environments

Transformative or Conservative? Conservation laws for ResNets and Transformers

Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization

UI-Vision: Desktop-centric GUI Benchmark for Visual Perception and Interaction

Understanding Bias Reinforcement in LLM Agents Debate

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

Understanding the Skill Gap in Recurrent Models: The Role of the Gather-and-Aggregate Mechanism

Unifews: You Need Fewer Operations for Efficient Graph Neural Networks

Unified Screening for Multiple Diseases

Uniform Mean Estimation via Median-of-Means for Heavy-Tailed Distributions

Unifying 2D and 3D Vision-Language Understanding

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design

Universal Approximation of Mean-Field Models via Transformers

Universal Neural Optimal Transport

Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities

Update Your Transformer to the Latest Release: Re-Basin of Task Vectors

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical Reasoning

Visual Autoregressive Modeling for Image Super-Resolution

ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy

VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians

What If We Recaption Billions of Web Images with LLaMA-3?

When Can Proxies Improve the Sample Complexity of Preference Learning?

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets

When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class

When to retrain a machine learning model

Which Attention Heads Matter for In-Context Learning?

"Why There Is a Tumor?": Safeguard Tumor Segmentation and Detection with Trustworthy Rationales

Winner-takes-all for Multivariate Probabilistic Time Series Forecasting

Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices

WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints

(ends 1:30 PM)

1 p.m.

Break:

Hosted Grab and Go Lunch

(ends 2:00 PM)

2 p.m.

Invited Talk:

Invited Talk - Pamela Samuelson

Pamela Samuelson

(ends 3:00 PM)

3:30 p.m.

Oral 2A Diffusion Models [3:30-4:30]

Orals 3:30-4:30

[3:30] DeFoG: Discrete Flow Matching for Graph Generation

[3:45] MGD$^3$ : Mode-Guided Dataset Distillation using Diffusion Models

[4:00] Inductive Moment Matching

[4:15] Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions

(ends 4:30 PM)

Oral 2B Positions: AI Regulation and Safety [3:30-4:30]

Orals 3:30-4:30

[3:30] Position: Generative AI Regulation Can Learn from Social Media Regulation

[3:45] Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal Noncompliance

[4:00] Position: AI Agents Need Authenticated Delegation

[4:15] Position: AI Safety should prioritize the Future of Work

(ends 4:30 PM)

Oral 2C Reinforcement Learning [3:30-4:30]

Orals 3:30-4:30

[3:30] Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration

[3:45] Temporal Difference Flows

[4:00] Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

[4:15] Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination

(ends 4:30 PM)

Oral 2D Efficient ML [3:30-4:30]

Orals 3:30-4:30

[3:30] AdaSplash: Adaptive Sparse Flash Attention

[3:45] Accelerating LLM Inference with Lossless Speculative Decoding for Heterogeneous Vocabularies

[4:00] ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

[4:15] Mixture of Lookup Experts

(ends 4:30 PM)

Oral 2E Optimal Transport [3:30-4:30]

Orals 3:30-4:30

[3:30] Hierarchical Refinement: Optimal Transport to Infinity and Beyond

[3:45] Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time

[4:00] Flowing Datasets with Wasserstein over Wasserstein Gradient Flows

[4:15] Addressing Misspecification in Simulation-based Inference through Data-driven Calibration

(ends 4:30 PM)

4:30 p.m.

Break:

Coffee Break

(ends 5:30 PM)

Poster Session 2 [4:30-7:00]

Posters 4:30-7:00

Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data

Constrain Alignment with Sparse Autoencoders

CTBench: A Library and Benchmark for Certified Training

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations

In-Context Learning and Occam's Razor

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment

Learning Classifiers That Induce Markets

One-step full gradient suffices for low-rank fine-tuning, provably and efficiently

On the Local Complexity of Linear Regions in Deep ReLU Networks

Policy-labeled Preference Learning: Is Preference Enough for RLHF?

Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards

SEMU: Singular Value Decomposition for Efficient Machine Unlearning

SPRI: Aligning Large Language Models with Context-Situated Principles

Sundial: A Family of Highly Capable Time Series Foundation Models

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

The Underlying Universal Statistical Structure of Natural Datasets

Tree-Sliced Wasserstein Distance: A Geometric Perspective

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data

Understanding Generalization in Quantum Machine Learning with Margins

$\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints

Accelerated Diffusion Models via Speculative Sampling

Accelerating LLM Inference with Lossless Speculative Decoding for Heterogeneous Vocabularies

Accurate Identification of Communication Across Multiple Interacting Neural Populations

A Certified Unlearning Approach without Access to Source Data

A Contextual Online Learning Theory of Brokerage

Action-Dependent Optimality-Preserving Reward Shaping

Active Reward Modeling: Adaptive Preference Labeling for Large Language Models

Active Treatment Effect Estimation via Limited Samples

Adapting to Evolving Adversaries with Regularized Continual Robust Training

Adaptive kernel predictors from feature-learning infinite limits of neural networks

Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection

AdaSplash: Adaptive Sparse Flash Attention

ADDQ: Adaptive distributional double Q-learning

Addressing Misspecification in Simulation-based Inference through Data-driven Calibration

ADIOS: Antibody Development via Opponent Shaping

AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Adversarial Robust Generalization of Graph Neural Networks

Adversaries Can Misuse Combinations of Safe Models

AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation

A General Representation-Based Approach to Multi-Source Domain Adaptation

A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity

Agent-as-a-Judge: Evaluate Agents with Agents

Agent Reviewers: Domain-specific Multimodal Agents with Shared Memory for Paper Review

Algorithmic Recourse for Long-Term Improvement

Algorithms with Calibrated Predictions

A Manifold Perspective on the Statistical Generalization of Graph Neural Networks

A Meta-learner for Heterogeneous Effects in Difference-in-Differences

Analytical Lyapunov Function Discovery: An RL-based Generative Approach

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

An Analysis of Quantile Temporal-Difference Learning

An Augmentation-Aware Theory for Self-Supervised Contrastive Learning

An Effective and Secure Federated Multi-View Clustering Method with Information-Theoretic Perspective

An efficient search-and-score algorithm for ancestral graphs using multivariate information scores

An in depth look at the Procrustes-Wasserstein distance: properties and barycenters

An Instrumental Value for Data Production and its Application to Data Pricing

A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations

any4: Learned 4-bit Numeric Representation for LLMs

A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents

Are High-Quality AI-Generated Images More Difficult for Models to Detect?

Are Large Brainwave Foundation Models Capable Yet ? Insights from Fine-Tuning

A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations

A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?

Attention-aware Post-training Quantization without Backpropagation

Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data

Attention-Only Transformers via Unrolled Subspace Denoising

At the Edge of Laziness: Scaling Limits of Catastrophic Forgetting

A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal Regression

A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features

AutoCATE: End-to-End, Automated Treatment Effect Estimation

Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios

A Variational Information Theoretic Approach to OOD Detection

Balanced Learning for Domain Adaptive Semantic Segmentation

Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing

BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training

BARNN: A Bayesian Autoregressive and Recurrent Neural Network

Batch List-Decodable Linear Regression via Higher Moments

BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation

Bayesian basis function approximation for scalable Gaussian process priors in deep generative models

BECAME: Bayesian Continual Learning with Adaptive Model Merging

Benchmarking Quantum Reinforcement Learning

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression

Benign Overfitting in Token Selection of Attention Mechanism

Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning

Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance

Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning

Beyond One-Hot Labels: Semantic Mixing for Model Calibration

Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Systems?

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models

Black-Box Adversarial Attacks on LLM-Based Code Completion

Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation

BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in Healthcare

Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO*

Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing

CALM: Consensus-Aware Localized Merging for Multi-Task Learning

Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers

Can We Predict Performance of Large Models across Vision-Language Tasks?

Causal Invariance-aware Augmentation for Brain Graph Contrastive Learning

Causality Inspired Federated Learning for OOD Generalization

CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning

Certified Unlearning for Neural Networks

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off

Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies

Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World

CommVQ: Commutative Vector Quantization for KV Cache Compression

Complete-Tree Space Favors Data-Efficient Link Prediction

Compressed Image Generation with Denoising Diffusion Codebook Models

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Concept Reachability in Diffusion Models: Beyond Dataset Constraints

Conformity Score Averaging for Classification

Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium

Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré-Hopf Theorem

Contextual Bandits for Unbounded Context Distributions

Contextures: Representations from Contexts

Continuous Bayesian Model Selection for Multivariate Causal Discovery

Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion

Contrastive Visual Data Augmentation

Control and Realism: Best of Both Worlds in Layout-to-Image without Training

Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration

Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning

CPCF: A Cross-Prompt Contrastive Framework for Referring Multimodal Large Language Models

CRANE: Expressive Grammar-Constrained LLM Generation

Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination

CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism

CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty

Curvature Enhanced Data Augmentation for Regression

CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection

DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models

Data Foundations for Large Scale Multimodal Clinical Foundation Models

David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training

Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision

DeFoG: Discrete Flow Matching for Graph Generation

Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization

Design Considerations in Offline Preference-based RL

Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models

D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation

DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra

Discovering Physics Laws of Dynamical Systems via Invariant Function Learning

Discovering Symbolic Cognitive Models from Human and Animal Behavior

Discrepancies are Virtue: Weak-to-Strong Generalization through an Intrinsic Dimension Lens

Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies

Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping

Distribution Matching with Structural Regularization via Expressive Score-Based Priors

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?

Does one-shot give the best shot? Mitigating Model Inconsistency in One-shot Federated Learning

DRAG: Data Reconstruction Attack using Guided Diffusion

DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization

Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning

DVI:A Derivative-based Vision Network for INR

EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation

Efficient ANN-SNN Conversion with Error Compensation Learning

Efficient Distributed Optimization under Heavy-Tailed Noise

Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset Distillation

Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks

e-GAI: e-value-based Generalized $\alpha$-Investing for Online False Discovery Rate Control

EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation

Ehrenfeucht-Haussler Rank and Chain of Thought

Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel

Elucidating the Design Space of Multimodal Protein Language Models

EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph

Empirical Privacy Variance

Empowering World Models with Reflection for Embodied Video Prediction

Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration

Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance

Enhancing Graph Invariant Learning from a Negative Inference Perspective

Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models

Enhancing Statistical Validity and Power in Hybrid Controlled Trials: A Randomization Inference Approach with Conformal Selective Borrowing

Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks

Ensemble Learned Bloom Filters: Two Oracles are Better than One

Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving

EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous Control

Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements

Exploring Invariance in Images through One-way Wave Equations

Exploring Vsion Semantic Prompt for Efficient Point Cloud Understanding

Extracting Rare Dependence Patterns via Adaptive Sample Reweighting

Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models

FairPFN: A Tabular Foundation Model for Causal Fairness

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks

Fast Min-$\epsilon$ Segmented Regression using Constant-Time Segment Merging

Feasible Action Search for Bandit Linear Programs via Thompson Sampling

FeatSharp: Your Vision Model Features, Sharper

Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions

FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates

Few-Shot Learner Generalizes Across AI-Generated Image Detection

Fine-Grained Video Captioning through Scene Graph Consolidation

Finite-Time Analysis of Discrete-Time Stochastic Interpolants

Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator

Fixing the Loose Brake: Exponential Tail Bounds for Stopping Time in Best Arm Identification

FLAM: Frame-Wise Language-Audio Modeling

Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning

Flexible Tails for Normalizing Flows

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions

FloE: On-the-Fly MoE Inference on Memory-constrained GPU

Flopping for FLOPs: Leveraging equivariance for computational efficiency

Flow-based Domain Randomization for Learning and Sequencing Robotic Skills

Flowing Datasets with Wasserstein over Wasserstein Gradient Flows

Fragments to Facts: Partial-Information Fragment Inference from LLMs

From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms

Fully compartmentalizing visual memory perception with procedural data

Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time

Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces

Fusing Reward and Dueling Feedback in Stochastic Bandits

Gap-Dependent Bounds for Federated $Q$-Learning

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models

GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation

Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View Learning

Generalization Analysis for Contrastive Representation Learning under Non-IID Settings

Generalization and Robustness of the Tilted Empirical Risk

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder

GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing

Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning

Graph Diffusion for Offline Multi-Agent Coordination

Gridded Transformer Neural Processes for Spatio-Temporal Data

G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration

Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms

Habitizing Diffusion Planning for Efficient and Effective Decision Making

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration

Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed Trees

Hierarchical Equivariant Policy via Frame Transfer

Hierarchical Refinement: Optimal Transport to Infinity and Beyond

Hierarchical Reinforcement Learning with Targeted Causal Interventions

Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series

HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks

How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective

(How) Do Language Models Track State?

How Far Is Video Generation from World Model: A Physical Law Perspective

How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Pre-training and Prompt Learning with Generalization Error

How to Steer LLM Latents for Hallucination Detection?

How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias

Hybrid Spiking Vision Transformer for Object Detection with Event Cameras

Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

Identifiable Object Representations under Spatial Ambiguities

Idiosyncrasies in Large Language Models

IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic

Implicit degree bias in the link prediction task

Implicit Subgraph Neural Network

Importance Corrected Neural JKO Sampling

Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation

Improved Online Confidence Bounds for Multinomial Logistic Bandits

Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers

Improving Model Alignment Through Collective Intelligence of Open-Source Models

Improving the statistical efficiency of cross-conformal prediction

Improving Transformer World Models for Data-Efficient RL

IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction

Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functionally Interpretability in Reinforcement Learning

Inverse Bridge Matching Distillation

KinDEL: DNA-Encoded Library Dataset for Kinase Inhibitors

Kinetic Langevin Diffusion for Crystalline Materials Generation

KV Shifting Attention Enhances Language Modeling

L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning

Label Distribution Propagation-based Label Completion for Crowdsourcing

LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Space Surpass the AR Models

Learn Beneficial Noise as Graph Augmentation

Learning Adaptive Lighting via Channel-Aware Guidance

Learning-Augmented Hierarchical Clustering

Learning Changes in Graphon Attachment Network Models

Learning Distances from Data with Normalizing Flows and Score Matching

Learning Fused State Representations for Control from Multi-View Observations

Learning Invariant Causal Mechanism from Vision-Language Models

Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms

Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks

Learning Progress Driven Multi-Agent Curriculum

Learnings from Scaling Visual Tokenizers for Reconstruction and Generation

Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains

Learning to Generate 3D Molecules via Language Models with Geometry-Aware Tokenization

Learning with a Reference Model: From Generalization Theory to Scaling Law

Learn Sharp Interface Solution by Homotopy Dynamics

Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection

Leveraging Offline Data in Linear Latent Contextual Bandits

Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries

LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations

Linear Contextual Bandits With Interference

Locality Preserving Markovian Transition for Instance Retrieval

LongRoPE2: Near-Lossless LLM Context Window Scaling

Low-Rank Thinning

LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers

Mahalanobis++: Feature Normalization as the Missing Ingredient for Reliable OOD Detection

Making Genomic Foundation Models more Foundational Requires Outlier Removal: A Case Study on DNABERT-2

Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding

MathConstruct: Challenging LLM Reasoning with Constructive Proofs

Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization

Measuring Diversity: Axioms and Challenges

MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge

MGD$^3$ : Mode-Guided Dataset Distillation using Diffusion Models

MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges

Mixture of Lookup Experts

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

Model-Based Exploration in Monitored Markov Decision Processes

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

MOGIC: METADATA-INFUSED ORACLE GUIDANCE FOR IMPROVED EXTREME CLASSIFICATION

Moment Matching Self-Distillation

Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport

More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions

MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning

Multiaccuracy and Multicalibration via Proxy Groups

Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding

Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference

MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation

Multi-View Graph Clustering via Node-Guided Contrastive Encoding

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning

Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems

Near-Optimal Sample Complexity for MDPs via Anchoring

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

Neural Event-Triggered Control with Optimal Scheduling

Neural Genetic Search in Discrete Spaces

Neural Graph Matching Improves Retrieval Augmented Generation in Small Molecule Mass Spectrum Prediction

Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment

Neurosymbolic World Models for Sequential Decision Making

Noise Conditional Variational Score Distillation

NoLiMa: Long-Context Evaluation Beyond Literal Matching

Nonparametric Identification of Latent Concepts: a Structural View

Non-stationary Diffusion For Probabilistic Time Series Forecasting

Off-Policy Evaluation under Nonignorable Missing Data

Olica: Efficient Structured Pruning of Large Language Models without Retraining

On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists

One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model Trajectory

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution

On Explaining Equivariant Graph Networks via Improved Relevance Propagation

Online Linear Classification with Massart Noise

Online Robust Reinforcement Learning Through Monte-Carlo Planning

On Temperature Scaling and Conformal Prediction of Deep Classifiers

On the Convergence of Continuous Single-timescale Actor-critic

On the Query Complexity of Verifier-Assisted Language Generation

On the Similarities of Embeddings in Contrastive Learning

On Understanding Attention-Based In-Context Learning for Categorical Data

Optimal Decision Tree Pruning Revisited: Algorithms and Complexity

Optimal Information Retention for Time-Series Explanations

Optimal Task Order for Continual Learning of Multiple Tasks

Optimization for Neural Operators can Benefit from Width

Optimization Proxies using Limited Labeled Data and Training Time -- A Semi-Supervised Bayesian Neural Network Approach

OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling

OrcaLoca: An LLM Agent Framework for Software Issue Localization

Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads

Overcoming Fake Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan

PAC-Bayes Analysis for Recalibration in Classification

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling

PaperBench: Evaluating AI’s Ability to Replicate AI Research

Parameter-Efficient Fine-Tuning of State Space Models

Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging

Patch-wise Structural Loss for Time Series Forecasting

PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs

Perceptual-GS: Scene-Adaptive Perceptual Densification for Gaussian Splatting

Perceptually Constrained Precipitation Nowcasting Model

Permutation Equivariant Neural Networks for Symmetric Tensors

PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction

Physics-Informed Generative Modeling of Wireless Channels

PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals

PoisonBench: Assessing Large Language Model Vulnerability to Poisoned Preference Data

Polynomial-Time Approximability of Constrained Reinforcement Learning

Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models

Position: AI Agents Need Authenticated Delegation

Position: AI Safety should prioritize the Future of Work

Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research

Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care

Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption

Position: Challenges and Future Directions of Data-Centric AI Alignment

Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal Noncompliance

Position: Editing Large Language Models Poses Serious Safety Risks

Position: Enough of Scaling LLMs! Lets Focus on Downscaling

Position: Formal Mathematical Reasoning—A New Frontier in AI

Position: Generative AI Regulation Can Learn from Social Media Regulation

Position: Graph Matching Systems Deserve Better Benchmarks

Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI

Position: Machine Learning Models Have a Supply Chain Problem

Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods

Position: We Need An Algorithmic Understanding of Generative AI

Potemkin Understanding in Large Language Models: Formalizing and Benchmarking Conceptual Comprehension

Prediction models that learn to avoid missing values

Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization

Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs

Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation

Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents

Prior-Informed Preference Alignment: as Plain Statistical Estimation

Prior Knowledge Guided Neural Architecture Generation

Private Model Personalization Revisited

Probably Approximately Global Robustness Certification

ProSec: Fortifying Code LLMs with Proactive Security Alignment

Protein Structure Tokenization: Benchmarking and New Recipe

Provably Efficient Exploration in Inverse Constrained Reinforcement Learning

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models

Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning

QT-DoG: Quantization-Aware Training for Domain Generalization

Ranked Entropy Minimization for Continual Test-Time Adaptation

Ranked from Within: Ranking Large Multimodal Models Without Labels

R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning

Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization

RedCrowd: Adaptive Security for LLMs

Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games

Redundancy Undermines the Trustworthiness of Self-Interpretable GNNs

Reflection-Window Decoding: Text Generation with Selective Refinement

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Regress, Don't Guess: A Regression-like Loss on Number Tokens for Language Models

Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning

Reinforce LLM Reasoning with Multi-Agent Reflection

Reinforcement Learning Control of a Physical Robot Device for Assisted Human Level Ground Walking without a Simulator

Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems

Relational Conformal Prediction for Correlated Time Series

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

Rethinking Aleatoric and Epistemic Uncertainty

Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation

Rethinking Prompt Design Space: In-Context Optimization through Evolutionary Self-replication

Retraining with Predicted Hard Labels Provably Increases Model Accuracy

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning

Revisiting Differentially Private Algorithms for Decentralized Online Learning

Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines

RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation

RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations

ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems

SADA: Stability-guided Adaptive Diffusion Acceleration

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

Safe-EF: Error Feedback for Non-smooth Constrained Optimization

Sample Complexity of Correlation Detection in the Gaussian Wigner Model

Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction

SAND: One-Shot Feature Selection with Additive Noise Distortion

Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation

Scalable Language Models with Posterior Inference of Latent Thought Vectors

Scalable Private Partition Selection via Adaptive Weighting

Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection

Scaling Laws for Pre-training Agents and World Models

SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval

ScoreMix: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions

Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI

Self-supervised Adversarial Purification for Graph Neural Networks

Semantics-aware Test-time Adaptation for 3D Human Pose Estimation

Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Sharper Stability and Generalization Analysis of Decentralized SGD

Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency

SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning

SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds

Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences

SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services

Solving Satisfiability Modulo Counting Exactly with Probabilistic Circuits

SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model

Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions

Star Attention: Efficient LLM Inference over Long Sequences

Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection

StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models

Steering Protein Language Models

Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design

Stochastic Deep Restoration Priors for Imaging Inverse Problems

Stochastic Encodings for Active Feature Acquistion

Stochastic Online Conformal Prediction with Semi-Bandit Feedback

Strategic Planning: A Top-Down Approach to Option Generation

Stray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density Clusters

Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation

Strong and Weak Identifiability of Optimization-based Causal Discovery

Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs

Subgoal-Guided Policy Heuristic Search with Learned Subgoals

Subgroups Matter for Robust Bias Mitigation

Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching

Survival analysis via density estimation

Synonymous Variational Inference for Perceptual Image Compression

TabICL: A Tabular Foundation Model for In-Context Learning on Large Data

Taming Rectified Flow for Inversion and Editing

Targeted Unlearning with Single Layer Unlearning Gradient

Task-agnostic Pre-training and Task-guided Fine-tuning for Versatile Diffusion Planner

Teaching Physical Awareness to LLMs through Sounds

Temporal Difference Flows

Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning

Test-time Correlation Alignment

Test-Time Graph Neural Dataset Search With Generative Projection

Text-to-LoRA: Instant Transformer Adaption

Textual Unlearning Gives a False Sense of Unlearning

Textural or Textual: How Vision-Language Models Read Text in Images

The Case for Learned Provenance-based System Behavior Baseline

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models

The Double-Ellipsoid Geometry of CLIP

The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli

The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes

Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models

The Polynomial Stein Discrepancy for Assessing Moment Convergence

The Price of Freedom: Exploring Tradeoffs in Equivariant Tensor Product Operations

The Price of Linear Time: Error Analysis of Structured Kernel Interpolation

The Role of Randomness in Stability

Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making

Tight and reliable conformal prediction

Time Series Representations with Hard-Coded Invariances

TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning

Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

Toward Data-centric Directed Graph Learning: An Entropy-driven Approach

Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer

Towards an Explainable Comparison of Feature Embeddings

Towards characterizing the value of edge embeddings in Graph Neural Networks

Towards Memorization Estimation: Fast, Formal and Free

Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback

TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian Prediction

TraffiX-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes

Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions

Transfer Q-Learning with Composite MDP Structures

Transformers are Deep Optimizers: Provable In-Context Learning for Deep Model Training

TS-SNN: Temporal Shift Module for Spiking Neural Networks

Ultra-Resolution Adaptation with Ease

UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein Distance

Unbiased and Economic LLM Evaluation via Synthetic Feedback

Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes

Understanding Chain-of-Thought in LLMs through Information Theory

Understanding Complexity in VideoQA via Visual Program Generation

Understanding High-Dimensional Bayesian Optimization

Understanding the Limits of Lifelong Knowledge Editing in LLMs

UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control

Unified K-Means Clustering with Label-Guided Manifold Learning

Unisolver: PDE-Conditional Transformers Are Universal Neural PDE Solvers

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment

Unlocking Post-hoc Dataset Inference with Synthetic Data

Unnatural Languages Are Not Bugs but Features for LLMs

Unsupervised Blind Speech Separation with a Diffusion Prior

Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors

Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision

VIP: Vision Instructed Pre-training for Robotic Manipulation

Volume-Aware Distance for Robust Similarity Learning

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Wasserstein Policy Optimization

Weak-to-Strong Generalization Even in Random Feature Networks, Provably

What can large language models do for sustainable food?

What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis

When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network

When to Forget? Complexity Trade-offs in Machine Unlearning

When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series

Whitened CLIP as a Likelihood Surrogate of Images and Captions

WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training

WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models

Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

World Model Implanting for Test-time Adaptation of Embodied Agents

WorldSimBench: Towards Video Generation Models as World Simulators

Wyckoff Transformer: Generation of Symmetric Crystals

Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models

Zero-Shot Offline Imitation Learning via Optimal Transport

(ends 7:00 PM)

WED 16 JUL

7:30 a.m.

Registration West

(ends 6:00 PM)

ICML Lounge Area:

ICML Lounge Area

(ends 7:00 PM)

Registration East

(ends 12:00 PM)

8 a.m.

Affinity Workshop:

WiML

(ends 5:30 PM)

8:30 a.m.

Test of Time Award

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

Exhibits

(ends 6:00 PM)

10 a.m.

Oral 3A Reasoning [10:00-11:00]

Orals 10:00-11:00

[10:00] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction

[10:15] Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark

[10:30] rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

[10:45] VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

(ends 11:00 AM)

Oral 3B Representations 1 [10:00-11:00]

Orals 10:00-11:00

[10:00] A Generalization Theory for Zero-Shot Prediction

[10:15] Statistical Test for Feature Selection Pipelines by Selective Inference

[10:30] Learning with Expected Signatures: Theory and Applications

[10:45] Blink of an eye: a simple theory for feature localization in generative models

(ends 11:00 AM)

Oral 3C Data-Centric ML [10:00-11:00]

Orals 10:00-11:00

[10:00] Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models

[10:15] Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection

[10:30] SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs

[10:45] Improving the Scaling Laws of Synthetic Data with Deliberate Practice

(ends 11:00 AM)

Oral 3D Optimization [10:00-11:00]

Orals 10:00-11:00

[10:00] Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness

[10:15] An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions

[10:30] Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton

[10:45] General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization

(ends 11:00 AM)

Oral 3E Causality and Domain Generalization [10:00-11:00]

Orals 10:00-11:00

[10:00] One-Step Generalization Ratio Guided Optimization for Domain Generalization

[10:15] An Improved Clique-Picking Algorithm for Counting Markov Equivalent DAGs via Super Cliques Transfer

[10:30] Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules

[10:45] Sanity Checking Causal Representation Learning on a Simple Real-World System

(ends 11:00 AM)

11 a.m.

Poster Session 3 [11:00-1:30]

Posters 11:00-1:30

Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

A Selective Learning Method for Temporal Graph Continual Learning

Can Transformers Learn Full Bayesian Inference In Context?

Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction

Commute Graph Neural Networks

Controlled Generation with Equivariant Variational Flow Matching

Dimension-Independent Rates for Structured Neural Density Estimation

Dual Feature Reduction for the Sparse-group Lasso and its Adaptive Variant

Efficient Heterogeneity-Aware Federated Active Data Selection

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product

EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification

Geometric Representation Condition Improves Equivariant Molecule Generation

Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo

LAST SToP for Modeling Asynchronous Time Series

Learning to Stop: Deep Learning for Mean Field Optimal Stopping

LEMoN: Label Error Detection using Multimodal Neighbors

Leveraging Predictive Equivalence in Decision Trees

Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization

Multi-Session Budget Optimization for Forward Auction-based Federated Learning

NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones

Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails

One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation

PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models

Position: Contextual Integrity is Inadequately Applied to Language Models

Position: Societal Impacts Research Requires Benchmarks for Creative Composition Tasks

Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents

Rethinking Confidence and Thresholds in Pseudolabeling-based SSL

Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift

Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory

SAFE: Finding Sparse and Flat Minima to Improve Pruning

SafetyAnalyst: Interpretable, transparent, and steerable safety moderation for AI behavior

Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction

Stable Offline Value Function Learning with Bisimulation-based Representations

Theoretical guarantees on the best-of-n alignment policy

Towards a Formal Theory of Representational Compositionality

TransPL: Pseudo-Labeling via Code Transitions for Time Series Adaptation

video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model

Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning

WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

$S^2$FGL: Spatial Spectral Federated Graph Learning

3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors

AAAR-1.0: Assessing AI’s Potential to Assist Research

ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning

Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity

Accurate and Efficient World Modeling with Masked Latent Transformers

A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing

Achieving Linear Speedup and Optimal Complexity for Decentralized Optimization over Row-stochastic Networks

A Comprehensive Analysis on LLM-based Node Classification Algorithms

Active Fine-Tuning of Multi-Task Policies

Active learning for efficient discovery of optimal combinatorial perturbations

Active Learning with Selective Time-Step Acquisition for PDEs

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Adaptive Data Collection for Robust Learning Across Multiple Distributions

Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection

AdaWorld: Learning Adaptable World Models with Latent Actions

Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?

Adversarial Inception Backdoor Attacks against Reinforcement Learning

Adversarial Reasoning at Jailbreaking Time

Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery

Aligning Atomic Vision Language Concepts for Controllable Image Generation

Aligning LLMs by Predicting Preferences from User Writing Samples

A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models

A linear query lower bound for submodular maximization

AlphaPO - Reward shape matters for LLM alignment

A Market for Accuracy: Classification Under Competition

am-ELO: A Stable Framework for Arena-based LLM Evaluation

A Model of Place Field Reorganization During Reward Maximization

An Entropy-Based Model for Hierarchical Learning

An Improved Clique-Picking Algorithm for Counting Markov Equivalent DAGs via Super Cliques Transfers

An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions

A Polynomial-Delay Maximal Ancestral Graph Listing Algorithm

Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle

Armijo Line-search Makes (Stochastic) Gradient Descent Go Fast

ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning

A Theoretical Justification for Asymmetric Actor-Critic Algorithms

Attention-Level Speculation

A Unified Approach to Routing and Cascading for LLMs

A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO

AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation

AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling

AutoEval Done Right: Using Synthetic Data for Model Evaluation

Automated Benchmark Generation for Repository-Level Coding Tasks

Automatic Reward Shaping from Confounded Offline Data

Autoregressive Optimal Design for Language Models

Avoiding Catastrophe in Online Learning by Asking for Help

Backdoor Attacks in Token Selection of Attention Mechanism

BaxBench: Can LLMs Generate Correct and Secure Backends?

Bayesian Neural Scaling Laws Extrapolation with Prior-Fitted Networks

BCE vs. CE in Deep Feature Learning

Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders

Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute

Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination

Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation

Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity

Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

Blink of an eye: a simple theory for feature localization in generative models

BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference

Boosting Mesh Generation with Coordinates Merging

Boosting Virtual Agent Learning and Reasoning: A Step-wise, Multi-dimensional, and Generalist Reward Model with Benchmark

Bridging Fairness and Efficiency in Conformal Inference: A Surrogate-Assisted Group-Clustered Approach

Bridging the Gap: Competitive Neural Data Similarity with Biologically Plausible Temporal Credit Assignment Rules

Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition

CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation

CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention

Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?

Can Large Language Models Understand Intermediate Representations?

Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark

Can Transformers Reason Logically? A Study in SAT Solving

Capturing Temporal Dynamics in Large-Scale Tree Canopy Height Estimation

Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models

Categorical Schrödinger Bridge Matching

CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging

CEGA: A Cost-Effective Approach for Graph-Based Model Extraction Attacks

Censor Dependent Variational Inference

Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning

Code-Generated Graph Representations Using Multiple LLM Agents for Material Properties Prediction

COExpander: Adaptive Solution Expansion for Combinatorial Optimization

Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution

Combinatorial Reinforcement Learning with Preference Feedback

Communicating Activations Between Language Model Agents

Compositional Risk Minimization

Compute or Load KV Cache? Why Not Both?

Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows

COMRECGC: Global Graph Counterfactual Explainer through Common Recourse

Concept-Based Unsupervised Domain Adaptation

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization

Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images

Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach

Continual Reinforcement Learning by Planning with Online World Models

Continuously Updating Digital Twins using Large Language Models

Continuous Semi-Implicit Models: A Path Towards Consistency

Convergence of Consistency Model with Multistep Sampling under General Data Assumptions

Cooperation of Experts: Fusing Heterogeneous Information with Large Margin

CoPINN: Physical Informed Neural Network

CoreMatching: Co-adaptive Sparse Inference Framework for Comprehensive Acceleration of Vision Language Model

Correlated Errors in Large Language Models

Cross-City Latent Space Alignment for Consistency Region Embedding

Curvature-aware Graph Attention for PDEs on Manifolds

DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning

Data Differences over Scale (DataDos) Suite: How to Predict Best Pretraining Data with Small Experiments

Dataflow-Guided Neuro-Symbolic Language Models for Type Inference

Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making

DeepCrossAttention: Supercharging Transformer Residual Connections

Deep Fuzzy Multi-view Learning for Reliable Classification

De-mark: Watermark Removal in Large Language Models

Demeaned Sparse: Efficient Anomaly Detection by Residual Estimate

Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector

Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation

Differential Coding for Training-Free ANN-to-SNN Conversion

Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and Inference

Diffusion Adversarial Post-Training for One-Step Video Generation

Diffusion Instruction Tuning

Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation

Direct Prediction Set Minimization via Bilevel Conformal Classifier Training

DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction

Discovering Latent Structural Causal Models from Spatiotemporal Data

Discrete and Continuous Difference of Submodular Minimization

Discrete Markov Probabilistic Models

Discrete Neural Algorithmic Reasoning

Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data

Distillation Scaling Laws

Distributed Conformal Prediction via Message Passing

Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal

Distributional Diffusion Models with Scoring Rules

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

Diversified Flow Matching with Translation Identifiability

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

DLP: Dynamic Layerwise Pruning in Large Language Models

DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing

D-MoLE: Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning

Does Data Scaling Lead to Visual Compositional Generalization?

Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion

Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-Speech

Double Machine Learning for Causal Inference under Shared-State Interference

Doubly Robust Fusion of High-Dimensional Treatments for Policy Learning

DSBRouter: Solving Global Routing via Diffusion Schrodinger Bridge

DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination

EasyInv: Toward Fast and Better DDIM Inversion

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery

EditLord: Learning Code Transformation Rules for Code Editing

Efficient Control via Neural-Embedded Iterative Linear Quadratic Regulator

Efficient Diffusion Models for Symmetric Manifolds

Efficient Fine-Grained Guidance for Diffusion-Based Symbolic Music Generation

Efficient Jailbreaking of Open-Source LLMs in Inference Time

Efficiently Serving Large Multimodal Models Using EPD Disaggregation

Efficiently Vectorized MCMC on Modern Accelerators

Efficient Multi-Objective Learning under Preference Guidance: A First-Order Penalty Approach

Efficient Noise Calculation in Deep Learning-based MRI Reconstructions

EgoPrivacy: What Your First-Person Camera Says About You?

ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces

Emergent Response Planning in LLM

Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection

Empower Structure-based Molecule Optimization with Gradient Guidance

Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model

Enforcing Idempotency in Neural Networks

Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation

Enhancing Foundation Models with Federated Domain Knowledge Infusion

Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization

Enhancing Logits Distillation with Plug&Play Kendall's $\tau$ Ranking Loss

Enhancing Parallelism in Decentralized Stochastic Convex Optimization

EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

Ergodic Generative Flows

ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models

Estimating the Correctness of Language Model Predictions from Internal Causal Mechanisms

ETTA: Elucidating the Design Space of Text-to-Audio Models

Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators

EvoPress: Accurate Dynamic Model Compression via Evolutionary Search

Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs

Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement Learning

Explicit Preference Optimization: No Need for an Implicit Reward Model

Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization

ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts

Expressive Geometric Generative Modeling with Noise Conditioned Graph Networks

Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts

FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered Inference

FactTest: Factuality Testing in Large Language Models with Statistical Guarantees

Fair Clustering via Alignment

Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization

Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework

Field Matching: an Electrostatic Paradigm to Generate and Transfer Data

Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games

FlexControl: Computation-Aware ControlNet with Differentiable Router for Text-to-Image Generation

FlexiReID: Adaptive Mixture of Expert for Multi-modal Person Re-Identification

FlipAttack: Jailbreak LLMs via Flipping

Flow-field inference from neural data using deep recurrent networks

Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options

Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning

Foundation Model Insights and a Multi-model Approach for Superior Fine-grained One-shot Subset Selection

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining

Free Process Rewards without Process Labels

From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models

From Hours to Minutes: Achieving Lossless Acceleration in 100K-Token Long Sequence Generation

From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set

From Logits to Hierarchies: Hierarchical Clustering made Simple

From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications

From Pre-Training Foundation Models to Zero-Shot Prediction: Learning Paths, Prompt Complexity, and Residual Dependence

FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation

Function-Space Learning Rates

Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton

Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds

GCAL: Adapting Graph Models to Evolving Domain Shifts

General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization

Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series

Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction

Generative Data Mining with Longtail-Guided Diffusion

Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning

Geometric Hyena Networks for Large-scale Equivariant Learning

GPTQv2: Efficient Finetuning-Free Quantization for Asymmetric Calibration

Gradient Boosting Reinforcement Learning

GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation

Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

GTR: A General, Multi-View, and Dynamic Framework for Trajectory Representation Learning

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents

HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training

Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres

HEAP: Hyper Extended APDHG Operator for Constrained High-dim PDEs

Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources

Heterogeneous Label Shift: Theory and Algorithm

Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It

Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification

How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence

How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation

How to Synthesize Text Data without Model Collapse?

HyperIV: Real-time Implied Volatility Smoothing

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations

Identifying Causal Direction via Variational Bayesian Compression

Imitation Learning from a Single Temporally Misaligned Video

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling

Implicit Riemannian Optimism with Applications to Min-Max Problems

Impossible Videos

Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization Scheme

Improved learning via k-DTW: a novel dissimilarity measure for curves

Improving Consistency Models with Generator-Augmented Flows

Improving Diversity in Language Models: When Temperature Fails, Change the Loss

Improving the Effective Receptive Field of Message-Passing Neural Networks

Improving the Scaling Laws of Synthetic Data with Deliberate Practice

Inference-Time Alignment of LLMs via User-Specified Multi-Criteria Transfer Decoding

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models

INRFlow: Flow Matching for INRs in Ambient Space

Instruction-Following Pruning for Large Language Models

Integer Programming for Generalized Causal Bootstrap Designs

Interaction-Aware Gaussian Weighting for Clustered Federated Learning

Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence

Inverse Optimization via Learning Feasible Regions

Investigating Non-Transitivity in LLM-as-a-Judge

Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs

IT$^3$: Idempotent Test-Time Training

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning

Knowledge Retention in Continual Model-Based Reinforcement Learning

Knowledge Swapping via Learning and Unlearning

KoopSTD: Approximating Koopman Spectrum with Timescale Decoupling for Faithful Similarity Analysis between Dynamical Systems

LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization

Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups

Latent Diffusion Planning for Imitation Learning

Learning In-context $n$-grams with Transformers: \\ Sub-$n$-grams Are Near Stationary Points

Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision

Learning Parametric Distributions from Samples and Preferences

Learning Safety Constraints for Large Language Models

Learning Soft Sparse Shapes for Efficient Time-Series Classification

Learning State-Based Node Representations from a Class Hierarchy for Fine-Grained Open-Set Detection

Learning the Electronic Hamiltonian of Large Atomic Structures

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals

Learning to Steer Learners in Games

Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL

Learning with Expected Signatures: Theory and Applications

Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams

LensLLM: Unveiling Fine-Tuning Dynamics for LLM Selection

LETS Forecast: Learning Embedology for Time Series Forecasting

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration

LEVIS: Large Exact Verifiable Input Spaces for Neural Networks

LIFT-GS: Cross-Scene Render-Supervised Distillation for 3D Language Grounding

Liger: Linearizing Large Language Models to Gated Recurrent Structures

LightGTS: A Lightweight General Time Series Forecasting Model

Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty

Limitations of measure-first protocols in quantum machine learning

Linear convergence of Sinkhorn's algorithm for generalized static Schrödinger bridge

Linearization Turns Neural Operators into Function-Valued Gaussian Processes

LipsNet++: Unifying Filter and Controller into a Policy Network

LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces

LLMs can see and hear without any training

Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning

Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression

Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic

MARGE: Improving Math Reasoning with Guided Exploration

Mastering Board Games by External and Internal Planning with Language Models

MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations

Matryoshka Quantization

MCU: An Evaluation Framework for Open-Ended Game Agents

MedRAX: Medical Reasoning Agent for Chest X-ray

MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning

Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training

MetaAgent: Automatically Building Multi-Agent System based on Finite State Machine

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation

MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product

MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning

Mind the Gap: A Practical Attack on GGUF Quantization

Minimalist Concept Erasure in Generative Models

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance

Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

Modular Duality in Deep Learning

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

Monte Carlo Tree Diffusion for System 2 Planning

Morse: Fast Sampling for Accelerating Diffusion Models Universally

Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment

Multi-Objective Causal Bayesian Optimization

Multi-objective Linear Reinforcement Learning with Lexicographic Rewards

Multiple-policy Evaluation via Density Estimation

Multi-token prediction boosts creativity in open-ended algorithmic tasks

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback

Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks

NETS: A Non-equilibrium Transport Sampler

Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery

NeuronTune: Towards Self-Guided Spurious Bias Mitigation

NeuroTree: An Interpretable High-Order GCN for Learning Brain Pathways in Psychiatric Disorders

NExtLong: Toward Effective Long-Context Training without Long Documents

NICE: Non-differentiable Evaluation Metric-based Data Selection for Instruction Tuning

Nonconvex Theory of $M$-estimators with Decomposable Regularizers

Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness

No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces

Novelty Detection in Reinforcement Learning with World Models

Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference

Offline Opponent Modeling with Truncated Q-driven Instant Policy Refinement

On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization

One-Step Generalization Ratio Guided Optimization for Domain Generalization

On Fine-Grained Distinct Element Estimation

On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms

Online Learning with Unknown Constraints

On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness

On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics

On the Power of Learning-Augmented Search Trees

On the Provable Separation of Scales in Maximal Update Parameterization

On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents

On the Robustness of Reward Models for Language Model Alignment

Optimal Auction Design in the Joint Advertising

Optimal Error Bounds in $\mathcal{W}_2$-Distance with Sqrt(d) Dimension Dependence for Langevin Monte Carlo beyond Log-Concavity

Optimal Survey Design for Private Mean Estimation

Optimal transport-based conformal prediction

Outlier-Aware Post-training Quantization for Discrete Graph Diffusion Models

Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models

Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination’s Impact on Machine Translation

PAC Learning with Improvements

Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Partially Observable Reinforcement Learning with Memory Traces

PASS: Private Attributes Protection with Stochastic Data Substitution

PDUDT: Provable Decentralized Unlearning under Dynamic Topologies

Peri-LN: Revisiting Layer Normalization in the Transformer Architecture

Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data

Permutation-Free High-Order Interaction Tests

Physics Aware Neural Networks for Unsupervised Binding Energy Prediction

Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability

Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference

PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning

Point-Level Topological Representation Learning on Point Clouds

Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study

Policy Design for Two-sided Platforms with Participation Dynamics

POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization

Position: AI Evaluation Should Learn from How We Test Humans

Position: AI's growing due process problem

Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge

Position: General Intelligence Requires Reward-based Pretraining

Position: It Is Time We Test Neural Computation In Vitro

Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences

Position: Retrieval-augmented systems can be dangerous medical communicators

Position: When Incentives Backfire, Data Stops Being Human

Positive-unlabeled AUC Maximization under Covariate Shift

Predictive Consistency Learning with Gradual Label Modeling

Primitive Vision: Knowing Where to Look is Key in Math Diagram Understanding

Primphormer: Efficient Graph Transformers with Primal Representations

Principled Algorithms for Optimizing Generalized Metrics in Binary Classification

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

Probabilistic Factorial Experimental Design for Combinatorial Interventions

Probing Visual Language Priors in VLMs

Progressive Tempering Sampling with Diffusion

Prompt-based Depth Pruning of Large Language Models

Prompt-to-Leaderboard: Prompt-Adaptive Language Model Evaluations with Neural Coefficient Models

Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features

Proportional Multiwinner Voting with Dynamic Candidate Sets

Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent

Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity

Provable Zero-Shot Generalization in Offline Reinforcement Learning

Provably Efficient Algorithm for Best Scoring Rule Identification in Online Information Acquisition

Provably Improving Generalization of Few-shot models with Synthetic Data

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline

QuanONet: Quantum Neural Operator with Application to Differential Equation

Quantum Optimization via Gradient-Based Hamiltonian Descent

QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions

QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles for model-monitoring

Q-VDiT: Towards Accurate Quantization of Video-Generation Diffusion Transformers

RAGGED: Towards Informed Design of Scalable and Stable RAG Systems

RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals

REG: Rectified Gradient Guidance for Conditional Diffusion Models

Regularized Langevin Dynamics for Combinatorial Optimization

RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation

ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals

Return Capping: Sample Efficient CVaR Policy Gradient Optimisation

Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective

Revisiting the Predictability of Social Events

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reweighting Local Mimina with Tilted SAM

Robust Conformal Outlier Detection under Contaminated Reference Data

Robust Multi-bit Text Watermark with LLM-based Paraphrasers

Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs

Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization

RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Uniform and Vector Quantization

S4S: Solving for a Fast Diffusion Model Solver

SafeArena: Evaluating the Safety of Autonomous Web Agents

SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models

Safety Alignment Can Be Not Superficial With Explicit Safety Signals

Safety-Polarized and Prioritized Reinforcement Learning

Sample-specific Noise Injection for Diffusion-based Adversarial Purification

Sanity Checking Causal Representation Learning on a Simple Real-World System

Scalable Equilibrium Sampling with Sequential Boltzmann Generators

Scalable First-order Method for Certifying Optimal k-Sparse GLMs

Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching

SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming

SE(3)-Equivariant Diffusion Policy in Spherical Fourier Space

SEAD: Unsupervised Ensemble of Streaming Anomaly Detectors

SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding

SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning

SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning

Selective Response Strategies for GenAI

Self-Consistency Preference Optimization

Self-Discriminative Modeling for Anomalous Graph Detection

SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models

SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures

SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models

SHE: Streaming-media Hashing Retrieval

SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs

SlimLLM: Accurate Structured Pruning for Large Language Models

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels

Sounding that Object: Interactive Object-Aware Image to Audio Generation

Sparse Autoencoders, Again?

Sparse Autoencoders for Hypothesis Generation

Spatial Reasoning with Denoising Models

StaB-ddG: Predicting mutational effects on protein binding from folding energy

Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings

Statistical Test for Feature Selection Pipelines by Selective Inference

Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets

Stronger Neyman Regret Guarantees for Adaptive Experimental Design

Structured Preconditioners in Adaptive Optimization: A Unified Analysis

Subspace Optimization for Large Language Models with Convergence Guarantees

SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training

Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales

Symmetry-Aware GFlowNets

TabSDS: a lightweight, fully non-parametric, and model free approach for generating synthetic tabular data

Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion

Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neurons

Temporal Query Network for Efficient Multivariate Time Series Forecasting

Tensor Decomposition Based Memory-Efficient Incremental Learning

Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes

Test-Time Learning for Large Language Models

Test-Time Training Provably Improves Transformers as In-context Learners

The Elicitation Game: Evaluating Capability Elicitation Techniques

The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination

The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking

The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference

The Limits of Tractable Marginalization

The Noisy Laplacian: a threshold phenomenon for non-linear dimension reduction

Theoretical Guarantees for Robust Federated Model Evaluation

The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning

The Relationship Between No-Regret Learning and Online Conformal Prediction

The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training

Thinking LLMs: General Instruction Following with Thought Generation

Three-dimensional Trajectory Prediction with 3DMoTraj Dataset

Tightening Causal Bounds via Covariate-Aware Optimal Transport

TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting

Timing: Temporality-Aware Integrated Gradients for Time Series Explanation

Topological Signatures of Adversaries in Multimodal Alignments

TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

Towards the Causal Complete Cause of Multi-Modal Representation Learning

Towards Understanding Parametric Generalized Category Discovery on Graphs

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

Training Dynamics of In-Context Learning in Linear Attention

Training High Performance Spiking Neural Networks by Temporal Model Calibration

Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries

Trustworthy Machine Learning through Data-Specific Indistinguishability

TTFSFormer: A TTFS-based Lossless Conversion of Spiking Transformer

Tuning LLM Judge Design Decisions for 1/1000 of the Cost

UDora: A Unified Red Teaming Framework Against LLM Agents by Dynamically Leveraging Their Own Reasoning

Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory

Unconstrained Robust Online Convex Optimization

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach

Understanding the difficulties in posterior predictive estimation

Understanding the Logic of Direct Preference Alignment through Logic

Understanding the Unfairness in Network Quantization

Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data

Universal Approximation Theorem of Deep Q-Networks

Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective

Value-Based Deep RL Scales Predictably

Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations

Variational Learning of Fractional Posteriors

Variational Rectified Flow Matching

VerbalTS: Generating Time Series from Texts

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models

Visual Generation Without Guidance

WebOrganizer: Constructing Domains Enhances Pre-Training Data Curation

What makes a good feedforward computational graph?

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

WMAdapter: Adding WaterMark Control to Latent Diffusion Models

WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

Zero-Inflated Bandits

µnit Scaling: Simple and Scalable FP8 LLM Training

(ends 1:30 PM)

1 p.m.

Break:

Hosted Grab and Go Lunch

(ends 2:00 PM)

2 p.m.

Invited Talk:

Invited Talk - Frauke Kreuter

Frauke Kreuter

(ends 3:00 PM)

3:30 p.m.

Oral 4A Representations 2 [3:30-4:30]

Orals 3:30-4:30

[3:30] Sundial: A Family of Highly Capable Time Series Foundation Models

[3:45] Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

[4:00] Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data

[4:15] Equivalence is All: A Unified View for Self-supervised Graph Learning

(ends 4:30 PM)

Oral 4B Positions: Generative AI Evaluation [3:30-4:30]

Orals 3:30-4:30

[3:30] Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation

[3:45] Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity

[4:00] Position: Principles of Animal Cognition to Improve LLM Evaluations

[4:15] Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It

(ends 4:30 PM)

Oral 4C Privacy and Uncertainty Quantification [3:30-4:30]

Orals 3:30-4:30

[3:30] On Differential Privacy for Adaptively Solving Search Problems via Sketching

[3:45] Going Deeper into Locally Differentially Private Graph Neural Networks

[4:00] Auditing $f$-differential privacy in one run

[4:15] Conformal Prediction as Bayesian Quadrature

(ends 4:30 PM)

Oral 4D Applications in Science and Language [3:30-4:30]

Orals 3:30-4:30

[3:30] AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models

[3:45] Long-Form Speech Generation with Spoken Language Models

[4:00] Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes

[4:15] Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction

(ends 4:30 PM)

Oral 4E Algorithms [3:30-4:30]

Orals 3:30-4:30

[3:30] Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance

[3:45] High-Dimensional Prediction for Sequential Decision Making

[4:00] Near-Optimal Decision Trees in a SPLIT Second

[4:15] Expected Variational Inequalities

(ends 4:30 PM)

4:30 p.m.

Break:

Coffee Break

(ends 5:30 PM)

Poster Session 4 [4:30-7:00]

Posters 4:30-7:00

Approximate Differential Privacy of the $\ell_2$ Mechanism

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning

Conformal Anomaly Detection in Event Sequences

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions

NestQuant: nested lattice quantization for matrix product and LLMs

Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints

What Makes an Ensemble Hard to Interpret? A Theoretical Approach

$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation

3D Question Answering via only 2D Vision-Language Models

Accelerating PDECO by the Derivative of Neural Operators

Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach

A Closer Look at Backdoor Attacks on CLIP

A Closer Look at Multimodal Representation Collapse

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD

Activation Space Interventions Can Be Transferred Between Large Language Models

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation

Adaptive Elicitation of Latent Information Using Natural Language

Adaptive Estimation and Learning under Temporal Distribution Shift

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations

Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets

AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models

AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment

A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition

A General-Purpose Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments

Agent Workflow Memory

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Aligned Multi Objective Optimization

Almost Optimal Fully Dynamic $k$-Center Clustering with Recourse

A Mixture-Based Framework for Guiding Diffusion Models

An Analysis for Reasoning Bias of Language Models with Small Initialization

An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks

Angle-Robust Networks based on Gamma Distribution PCA for SAR Target Recognition

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning

AnyEdit: Edit Any Knowledge Encoded in Language Models

Anytime-Constrained Equilibria in Polynomial Time

A Online Statistical Framework for Out-of-Distribution Detection

A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization

A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data

A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems

Approximately Correct Label Distribution Learning

A Theoretical Framework For Overfitting In Energy-based Modeling

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization

A Theory for Conditional Generative Modeling on Multiple Data Sources

A Three-Branch Checks-and-Balances Framework for Context-Aware Ethical Alignment of Large Language Models

Attributes Shape the Embedding Space of Face Recognition Models

Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities

Auditing $f$-differential privacy in one run

A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation

AuPair: Golden Example Pairs for Code Repair

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

Autonomy-of-Experts Models

Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving

A Variational Framework for Improving Naturalness in Generative Spoken Language Models

Average Certified Radius is a Poor Metric for Randomized Smoothing

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms

BARK: A Fully Bayesian Tree Kernel for Black-box Optimization

Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models

Better-than-2 Approximation for Constrained Correlation Clustering

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts

Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

Beyond Pointwise Intervention: Learning Distribution-wise Control in Representation Space for Langauge Models

BiMark: Unbiased Multilayer Watermarking for Large Language Models

Binary Hypothesis Testing for Softmax Models and Leverage Score Models

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation

Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners

Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples

Boosting Protein Graph Representations through Static-Dynamic Fusion

Breaking Barriers: Combinatorial Algorithms for Non-monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation

Breaking Barriers in Hard Samples: Guiding the Generation of Synthetic Data for Medical Tasks with Data-centric Approach

BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimisation and Diffusion Modelling

BSO: Binary Spiking Online Optimization

Calibrated Language Models and How to Find Them with Label Smoothing

Can Large Language Models Ask the Right Questions in Solving Complex Problems with Incomplete Information?

Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection

CFP-GEN: Combinatorial Functional Protein Generation via Diffusion Language Models

Channel Normalization for Time Series Channel Identification

Chip Placement with Diffusion Models

CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries

Clone-Robust AI Alignment

Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling

Clustering via Self-Supervised Diffusion

CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization

COGNATE: Learning-Based Acceleration of Sparse Tensor Programs on Emerging Hardware

CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention

COKE: Core Kernel for More Efficient Approximation of Kernel Weights in Multiple Kernel Clustering

Come Together, But Not Right Now: A Simple Strategy to Boost Low-Rank Adaptation

Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries

Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training

Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation

Componential Prompt-Knowledge Alignment for Domain Incremental Learning

Compressing tree ensembles through Level-wise Optimization and Pruning

Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead

Concentration Distribution Learning from Label Distributions

Conditioning Diffusions Using Malliavin Calculus

Conformal Prediction as Bayesian Quadrature

Connecting Thomson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret

Consensus Based Stochastic Optimal Control

Constrained belief updating explains geometric structures in transformer representations

Constrained Online Convex Optimization with Polyak Feasibility Steps

Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games

Contradiction Retrieval via Contrastive Learning with Sparsity

Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification

Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning

Core Context Aware Transformers for Long Context Language Modeling

Core Knowledge Deficits in Multi-Modal Language Models

Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems

Cradle: Empowering Foundation Agents towards General Computer Control

Cross-Modal Alignment via Variational Copula Modelling

Cross-regularization: Adaptive Model Complexity through Validation Gradients

CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features

CursorCore: Assist Programming through Aligning Anything

DAMO: Data- and Model-aware Alignment of Multi-modal LLMs

DDAD: A Two-Pronged Adversarial Defense Based on Distributional Discrepancy

Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer

Determinant Estimation under Memory Constraints and Neural Scaling Laws

Differentiable Structure Learning with Ancestral Constraints

Differential privacy guarantees of Markov chain Monte Carlo algorithms

Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts

Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain

Diffusion-Nested Non-Autoregressive Transformer for the Synthesis and Imputation of Heterogeneous Tabular Data

Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning

DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models

DIME: Diffusion-Based Maximum Entropy Reinforcement Learning

Dimensionality Reduction on Complex Vector Spaces for Euclidean Distance with Dynamic Weights

DIS-CO: Discovering Copyrighted Content in VLMs Training Data

Discriminative Policy Optimization for Token-Level Reward Models

Disentangled Graph Spectral Domain Adaptation

Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts

Disentangling Sequence Memorization and General Capability in LLMs

Disparate Conditional Prediction in Multiclass Classifiers

Distributionally Robust Policy Learning under Concept Drifts

Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective

Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training

Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space

Do We Really Need Message Passing in Brain Network Modeling?

DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation

DPO Meets PPO: Reinforced Token Optimization for RLHF

DriveGPT: Scaling Autoregressive Behavior Models for Driving

DS-VLM: Diffusion Supervision Vision Language Model

Dueling Convex Optimization with General Preferences

DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications

Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data

EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization

EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph

Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges

EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction

Efficient and Separate Authentication Image Steganography Network

Efficient Core-set Selection for Deep Learning Through Squared Loss Minimization

Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling

Efficient LiDAR Reflectance Compression via Scanning Serialization

Efficient Long Context Fine-tuning with Chunk Flow

Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination

Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis

Efficient Robotic Policy Learning via Latent Space Backward Planning

Efficient Skill Discovery via Regret-Aware Optimization

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging

Embedding Safety into RL: A New Take on Trust Region Methods

Emotional Face-to-Speech

Empirical Design in Reinforcement Learning

Empowering Time Series Foundation Models with Sparse Mixture of Experts

Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story

Enhancing Spectral GNNs: From Topology and Perturbation Perspectives

Equivalence is All: A Unified View for Self-supervised Graph Learning

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks

Event-Customized Image Generation

EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams

Evolving Minds: Logic-Informed Inference from Temporal Action Patterns

Exogenous Isomorphism for Counterfactual Identifiability

Expected Variational Inequalities

Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models

Exploring Representations and Interventions in Time Series Foundation Models

Exponential Family Variational Flow Matching for Tabular Data Generation

FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems

FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation

Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness

Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective

Faster Global Minimum Cut with Predictions

Fast Incomplete Multi-view Clustering by Flexible Anchor Learning

Fast Tensor Completion via Approximate Richardson Iteration

Feature Shift Localization Network

Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation

Federated Learning for Feature Generalization with Convex Constraints

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning

FlatQuant: Flatness Matters for LLM Quantization

Flow Q-Learning

Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models

From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering

Fully Dynamic Embedding into $\ell_p$ Spaces

FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch

Functional Alignment Can Mislead: Examining Model Stitching

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

Generalization Analysis for Controllable Learning

Generalization of noisy SGD in unbounded non-convex settings

Generalization Performance of Ensemble Clustering: From Theory to Algorithm

Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models

Generalized additive models via direct optimization of regularized decision stump forests

Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction

Geometric Algebra Planes: Convex Implicit Neural Volumes

Geometric Contact Flows: Contactomorphisms for Dynamics and Control

Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems

GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras

GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for (Adaptive) Generalized Linear Low-Rank Trace Regression

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Going Deeper into Locally Differentially Private Graph Neural Networks

Gradient-based Explanations for Deep Learning Survival Models

Graph4MM: Weaving Multimodal Learning with Structural Information

Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models

Graph Inverse Style Transfer for Counterfactual Explainability

Graph Minimum Factor Distance and Its Application to Large-Scale Graph Data Clustering

Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation

Graph World Model

GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers

Grokking at the Edge of Linear Separability

Grokking Beyond the Euclidean Norm of Model Parameters

GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models

Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery

Hardware and Software Platform Inference

Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks

Hidden No More: Attacking and Defending Private Third-Party LLM Inference

Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals

High-Dimensional Prediction for Sequential Decision Making

High-Fidelity Simultaneous Speech-To-Speech Translation

How Expressive are Knowledge Graph Foundation Models?

Hyperband-based Bayesian Optimization for Black-box Prompt Selection

HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting

Hyper-Transforming Latent Diffusion Models

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity

Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions

Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms

Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance

Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging

Improving LLM Safety Alignment with Dual-Objective Optimization

Improving Rationality in the Reasoning Process of Language Models through Self-playing Game

Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Improving Zero-Shot Adversarial Robustness in VLMs by Closed-form Alignment of Adversarial Path Simplices

In-Context Fine-Tuning for Time-Series Foundation Models

Info-Coevolution: An Efficient Framework for Data Model Coevolution

Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models

Invariant Deep Uplift Modeling for Incentives Assignment in Online Marketing via Probability of Necessity and Sufficiency

Inverse problems with experiment-guided AlphaFold

Is Complex Query Answering Really Complex?

Iterative Vectors: In-Context Gradient Steering without Backpropagation

K$^2$IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson Processes

KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

Kernel Quantile Embeddings and Associated Probability Metrics

KGMark: A Diffusion Watermark for Knowledge Graphs

KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation

Large Language-Geometry Model: When LLM meets Equivariance

Latent Mamba Operator for Partial Differential Equations

Latent Variable Estimation in Bayesian Black-Litterman Models

Layer Caching for Accelerated Inference in Real-Time Rendering

LEAPS: A discrete neural sampler via locally equivariant networks

Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning

Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales

Learning Configurations for Data-Driven Multi-Objective Optimization

Learning from others' mistakes: Finetuning machine translation models with span-level error annotations

Learning Imbalanced Data with Beneficial Label Noise

Learning Input Encodings for Kernel-Optimal Implicit Neural Representations

Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction

Learning Survival Distributions with the Asymmetric Laplace Distribution

Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes

Learning to Route LLM with Confidence Tokens

Learning with Selectively Labeled Data from Multiple Decision-makers

Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control

Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models

Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation

Leveraging Reasoning with Guidelines to Elicit and Utilize Knowledge for Enhancing Safety Alignment

LieRE: Lie Rotational Positional Encodings

Lightspeed Geometric Dataset Distance via Sliced Optimal Transport

Lightweight Protocols for Distributed Private Quantile Estimation

LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning

LineFlow: A framework to learn active control of production lines

LLM-Augmented Chemical Synthesis and Design Decision Programs

LLM Data Selection and Utilization via Dynamic Bi-level Optimization

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models

Local Identifying Causal Relations in the Presence of Latent Variables

Long-Context Inference with Retrieval-Augmented Speculative Decoding

Long-Form Speech Generation with Spoken Language Models

Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space

LSCD: Lomb--Scargle Conditioned Diffusion for Irregular Time series Imputation

MAPLE: Many-Shot Adaptive Pseudo-Labeling In-Context Learning

MAPSparse: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer

Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection

Maximum Total Correlation Reinforcement Learning

Maximum Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators

MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models

Mechanisms of Projective Composition of Diffusion Models

MELON: Indirect Prompt Injection Defense via Masked Re-execution and Tool Comparison

MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs

Meta-Reinforcement Learning with Human-in-the-Loop Adaptation via Preference-Order-Preserving Task Embedding

MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text Decoding

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost

Multi-Turn Code Generation Through Single-Step Rewards

MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition

N2GON: Neural Networks for Graph-of-Net with Position Awareness

NEAR: Neural Electromagnetic Array Response

Near Optimal Best Arm Identification for Clustered Bandits

Near-Optimal Decision Trees in a SPLIT Second

Nesterov Method for Asynchronous Pipeline Parallel Optimization

New Bounds for Sparse Variational Gaussian Processes

Nonlinear transformers can perform inference-time feature learning: a case study of in-context learning on single-index models

Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics

Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition

OmniArch: Building the Foundation Model for Scientific Computing

On Differential Privacy for Adaptively Solving Search Problems via Sketching

One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs

One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models

Online Detecting LLM-Generated Texts via Sequential Hypothesis Testing by Betting

Online Episodic Convex Reinforcement Learning

Online Laplacian-Based Representation Learning in Reinforcement Learning

Online Pre-Training for Offline-to-Online Reinforcement Learning

On Measuring Long-Range Interactions in Graph Neural Networks

On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback

On the Duality between Gradient Transformations and Adapters

On the Out-of-Distribution Generalization of Self-Supervised Learning

On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains

Open-Det: An Efficient Learning Framework for Open-Ended Detection

Optimal Fair Learning Robust to Adversarial Distribution Shift

Optimizing Adaptive Attacks against Watermarks for Language Models

Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design

Optimizing Temperature for Language Models with Multi-Sample Inference

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Lanuge Model Inference

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

Output Alignment: A Fresh Perspective on Length Generalization in LLMs

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

OW-VAP: Visual Attribute Parsing for Open World Object Detection

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

PARQ: Piecewise-Affine Regularized Quantization

Parrot: Multilingual Visual Instruction Tuning

Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data

PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion

Persistent Topological Features in Large Language Models

Pfeife: Automatic Pipeline Parallelism for PyTorch

Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness

PILAF: Optimal Human Preference Sampling for Reward Modeling

Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule

PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models

Policy Regret Minimization in Markov Games with Function Approximation

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning

polybasic Speculative Decoding Through a Theoretical Perspective

Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation

Position: AI Should Not Be An Imitation Game: Centaur Evaluations

Position: All Current Generative Fidelity and Diversity Metrics are Flawed

Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.

Position: Human Baselines in Model Evaluations Need Rigor and Transparency (With Recommendations & Reporting Checklist)

Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks

Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity

Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It

Position: Principles of Animal Cognition to Improve LLM Evaluations

Position: The Future of Bayesian Prediction Is Prior-Fitted

Position: The Most Expensive Part of an LLM *should* be its Training Data

Position: Theory of Mind Benchmarks are Broken for Large Language Models

Position: We Can’t Understand AI Using our Existing Vocabulary

Position: We Need Responsible, Application-Driven (RAD) AI Research

Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search

Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion

Prediction-aware Learning in Multi-Agent Systems

Prediction-Powered E-Values

Predictive Performance of Deep Quantum Data Re-uploading Models

Preference Adaptive and Sequential Text-to-Image Generation

Privacy Attacks on Image AutoRegressive Models

Privacy-Preserving Federated Convex Optimization: Balancing Partial Participation and Efficiency via Noise Cancellation

Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption

Private Federated Learning using Preference-Optimized Synthetic Data

Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes

Progressively Label Enhancement for Large Language Model Alignment

Projection Pursuit Density Ratio Estimation

Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble

Properties of Wasserstein gradient flows for the Sliced-Wasserstein distance

Proto Successor Measure: Representing the Behavior Space of an RL Agent

Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction

Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent

Provable Length Generalization in Sequence Prediction via Spectral Filtering

Provable Maximum Entropy Manifold Exploration via Diffusion Models

PTTA: Purifying Malicious Samples for Test-Time Model Adaptation

Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions

Quantifying Memory Utilization with Effective State-Size

Quantifying perturbation impacts for large language models

Quantifying Prediction Stability Under Fine-tuning Multiplicity in Tabular LLMs

Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes

Rate Constrained Optimized Training of Large Language Models

Reconstructing cell lineage trees from phenotypic features with metric learning

Rectifying Conformity Scores for Better Conditional Coverage

Reducing Confounding Bias without Data Splitting for Causal Inference via Optimal Transport

Refining Adaptive Zeroth-Order Optimization at Ease

Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc Regression

Regret-Free Reinforcement Learning for Temporal Logic Specifications

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective

Reinforced Lifelong Editing for Language Models

Reliable and Efficient Amortized Model-based Evaluation

Residual TPP: A unified lightweight approach for event stream data analysis

RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior

Rethink GraphODE Generalization within Coupled Dynamical System

Rethinking Benign Overfitting in Two-Layer Neural Networks

Rethinking the Bias of Foundation Model under Long-tailed Distribution

Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding

Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate

Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces

Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?

Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization

Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation

R.I.P.: Better Models by Survival of the Fittest Prompts

Robot-Gated Shared Autonomy with Adaptive Intervention Mechanism

Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering

RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control

RocketKV: Accelerating Long-Context LLM Inference via Two-stage KV Cache Compression

ROPO: Robust Preference Optimization for Large Language Models

RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost Strategy

Sable: a Performant, Efficient and Scalable Sequence Model for MARL

SAFER: A Calibrated Risk-Aware Tabular-Language Recommendation Model for Dynamic Treatment Regimes

SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation

Sample complexity of branch-length estimation by maximum likelihood

Sample Efficient Demonstration Selection for In-Context Learning

Sampling Binary Data by Denoising through Score Functions

SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion

Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up

Scalable Meta-Learning via Mixed-Mode Differentiation

Scalable Reinforcement Post-Training Beyond Static Human Prompts

Scaling Large Motion Models with Million-Level Human Motions

Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

Scaling sparse feature circuit finding for in-context learning

Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification

Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning

Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows

Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection

SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization

Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density

Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts

Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN

Simplifying DINO by Coding Rate Regularization

Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models

SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation

SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

SkipGPT: Each Token is One of a Kind

Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data

SLIM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression

Smooth Interpolation for Improved Discrete Graph Generative Models

Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs

Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems

SparseVLM: Visual Token Sparsification for Efficient Vision Language Models Inference

Spectral-Aware Reservoir Computing for Fast and Accurate Time Series Classification

Speculative Ensemble: Fast Large Language Model Ensemble via Speculation

SPHINX: Structural Prediction using Hypergraph Inference Network

SpikF: Spiking Fourier Network for Efficient Long-term Prediction

Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct Alignment

Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion

Steerable Transformers for Volumetric Data

Strategic A/B testing via Maximum Probability-driven Two-armed Bandit

Structure-Guided Large Language Models for Text-to-SQL Generation

Subobject-level Image Tokenization

Sub-Sequential Physics-Informed Learning with State Space Model

SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics

Super Deep Contrastive Information Bottleneck for Multi-modal Clustering

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering

SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation

Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs

Taming Diffusion for Dataset Distillation with High Representativeness

Taming Knowledge Conflicts in Language Models

Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion

TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change Awareness

Teaching Transformers Causal Reasoning through Axiomatic Training

Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models

The Complexity of Learning Sparse Superposed Features with Feedback

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

The Diffusion Duality

The Efficiency of Guidance in Diffusion Models for General Data Distribution

The Generalized Skew Spectrum of Graphs

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence

The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates through Large Deviations

The Limits of Predicting Agents from Behaviour

Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos

The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic Regularized Optimal Transport

Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision

To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers

Tokenized Bandit for LLM Decoding and Alignment

TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration

TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference

Topology-Aware Dynamic Reweighting for Node Classification under Distribution Shifts

Toward a Unified Theory of Gradient Descent under Generalized Smoothness

Towards a Mechanistic Explanation of Diffusion Model Generalization

Towards Large Language Models with Greater Activation Sparsity

Towards Learning Generalities Across Graphs via Task-Trees

Towards Lifelong Model Editing via Simulating Ideal Editor

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks

TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation

Tree-Sliced Wasserstein Distance with Nonlinear Projection

TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories

UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models

Unbiased Evaluation of Large Language Models from a Causal Perspective

UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model

Understanding and Improving Length Generalization in Recurrent Models

Understanding Fixed Predictions via Confined Regions

Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts

Understanding the Accuracy-Communication Trade-off in Personalized Federated Learning

Understanding the Emergence of Multimodal Representation Alignment

Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra

Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach

UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules

Universal Length Generalization with Turing Programs

Unlocking the Power of SAM 2 for Few-Shot Segmentation

Vision Graph Prompting via Semantic Low-Rank Decomposition

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

Visual Abstraction: A Plug-and-Play Approach for Text-Visual Retrieval

Visual Graph Arena: Evaluating AI's Visual Conceptualization

Wait-Less Offline Tuning and Re-solving for Online Decision Making

Wasserstein Flow Matching: Generative Modeling Over Families of Distributions

Weakly Supervised Anomaly Detection via Dual-Tailed Kernel

Weakly-Supervised Contrastive Learning for Imprecise Class Labels

Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win

When and How Does CLIP Enable Domain and Compositional Generalization?

When Bad Data Leads to Good Models

When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration

When, Where and Why to Average Weights?

Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors

"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

XAttention: Unlocking the Power of Block Sparse Attention with Antidiagonal Scoring

X-Hacking: The Threat of Misguided AutoML

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

You Get What You Give: Reciprocally Fair Federated Learning

Zero-Shot Generalization of GNNs over Distinct Attribute Domains

Zero Shot Generalization of Vision-Based RL Without Data Augmentation

(ends 7:00 PM)

THU 17 JUL

7:30 a.m.

Registration West

(ends 6:00 PM)

ICML Lounge Area:

ICML Lounge Area

(ends 5:00 PM)

Registration East

(ends 12:00 PM)

8:30 a.m.

Invited Talk:

Invited Talk - Anca Dragan

Anca Dragan

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

Exhibits

(ends 1:00 PM)

10 a.m.

Oral 5A Safety and Security [10:00-11:00]

Orals 10:00-11:00

[10:00] STAIR: Improving Safety Alignment with Introspective Reasoning

[10:15] AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses

[10:30] Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

[10:45] Model Immunization from a Condition Number Perspective

(ends 11:00 AM)

Oral 5B Deep Learning Algorithms [10:00-11:00]

Orals 10:00-11:00

[10:00] DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

[10:15] ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

[10:30] Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning

[10:45] From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control

(ends 11:00 AM)

Oral 5C Probablistic Models [10:00-11:00]

Orals 10:00-11:00

[10:00] Rényi Neural Processes

[10:15] A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization

[10:30] Score Matching with Missing Data

[10:45] Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs

(ends 11:00 AM)

Oral 5D Applications in Math and Physics [10:00-11:00]

Orals 10:00-11:00

[10:00] The dark side of the forces: assessing non-conservative force models for atomistic machine learning

[10:15] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

[10:30] Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?

[10:45] Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics

(ends 11:00 AM)

Oral 5E Learning Theory [10:00-11:00]

Orals 10:00-11:00

[10:00] Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise

[10:15] All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance

[10:30] A Generalization Result for Convergence in Learning-to-Optimize

[10:45] Theoretical Limitations of Ensembles in the Age of Overparameterization

(ends 11:00 AM)

11 a.m.

Poster Session 5 [11:00-1:30]

Posters 11:00-1:30

A Versatile Influence Function for Data Attribution with Non-Decomposable Loss

CASE-Bench: Context-Aware Safety Evaluation Benchmark for Large Language Models

Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization

Independence Tests for Language Models

InfAlign: Inference-aware language model alignment

Learning Utilities from Demonstrations in Markov Decision Processes

Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective

Metadata Conditioning Accelerates Language Model Pre-training

Online Learning in Risk Sensitive constrained MDP

On Path to Multimodal Generalist: Levels and Benchmarks

On the Emergence of Position Bias in Transformers

Optimizing Noise Distributions for Differential Privacy

OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition

Positional Attention: Expressivity and Learnability of Algorithmic Computation

Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss

Scalable Gaussian Processes with Latent Kronecker Structure

Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic Stochastic Manipulations

$\epsilon$-VAE: Denoising as Visual Decoding

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

A Bregman Proximal Viewpoint on Neural Operators

Accelerating Spectral Clustering under Fairness Constraints

A Classification View on Meta Learning Bandits

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs

Actor-Critics Provably Achieve Optimal Sample Efficiency With General Function Approximation

Adapting Precomputed Features for Efficient Graph Condensation

Adaptive Flow Matching for Resolving Small-Scale Physics

Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference Time

Adaptive Partitioning Schemes for Optimistic Optimization

Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation

AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization

Adjoint Sampling: Highly-Scalable Diffusion Samplers via Adjoint Matching

Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees

Adversarial Robustness via Deformable Convolution with Stochasticity

Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks

A Generalization Result for Convergence in Learning-to-Optimize

A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings

Algorithms and Hardness for Active Learning on Graphs

Aligning Spoken Dialogue Models from User Interactions

All-atom Diffusion Transformers

All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance

AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning

AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement

A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-Making

An Architecture Search Framework for Inference-Time Techniques

A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization

An Efficient Pruner for Large Language Model with Theoretical Guarantee

An Expressive and Self-Adaptive Dynamical System for Efficient Equation Learning

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks

An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints

Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning Trees

Approximating Latent Manifolds in Neural Networks via Vanishing Ideals

A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games

Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning

A Two-Stage Learning-to-Defer Approach for Multi-Task Learning

AudioSpace: Generating Spatial Audio from 360-Degree Video

A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization

AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

Automatically Interpreting Millions of Features in Large Language Models

Automating Benchmark Curation from Crowdsourced Data

AutoStep: Locally adaptive involutive MCMC

Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts

BAnG: Bidirectional Anchored Generation for Conditional RNA Design

Banyan: Improved Representation Learning with Explicit Structure

Bayesian Consensus Prediction for Correlated Human Experts and Classifiers

Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds

Bayesian Weight Enhancement with Stead-State Adaptation for Test-time Adaptation in Dynamic Environments

BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning

Best of Both Worlds: Regret Minimization versus Minimax Play

Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance

Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning

Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs

Beyond the Lazy versus Rich Dichotomy: Geometry Insights in Feature Learning from Task-Relevant Manifold Untangling

Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC

Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective

BOOD: Boundary-based Out-Of-Distribution Data Generation

Breaking the $n^{1.5}$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition

Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries

Bridging Layout and RTL: Knowledge Distillation based Timing Prediction

Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models

BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression

Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?

Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs

CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models

Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

Catoni Contextual Bandits are Robust to Heavy-tailed Rewards

Causal Abstraction Inference under Lossy Representations

Causal Attribution Analysis for Continuous Outcomes

Causal Discovery from Conditionally Stationary Time Series

Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants

Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel

Certification for Differentially Private Prediction in Gradient-Based Training

Closed-form Solutions: A New Perspective on Solving Differential Equations

CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning

Collapse-Proof Non-Contrastive Self-Supervised Learning

Compact Matrix Quantum Group Equivariant Neural Networks

Compositional Flows for 3D Molecule and Synthesis Pathway Co-design

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Computing Voting Rules with Improvement Feedback

Consensus Is All You Get: The Role of Attention in Transformers

Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents

Correlation Clustering Beyond the Pivot Algorithm

Cost-efficient Collaboration between On-device and Cloud Language Models

Counting atoms faster: policy-based nuclear magnetic resonance pulse sequencing for atomic abundance measurement

Counting in small transformers: The delicate interplay between attention and feed-forward layers

Cover learning for large-scale topology representation

Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability

Curse of High Dimensionality Issue in Transformer for Long Context Modeling

Customizing the Inductive Biases of Softmax Attention using Structured Matrices

Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development

DCBM: Data-Efficient Visual Concept Bottleneck Models

DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space

DEALing with image reconstruction: Deep Attentive Least squares

Decision-aware training of spatiotemporal forecasting models to select a top K subset of sites for intervention

Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets

Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents

De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs

Deep Electromagnetic Structure Design Under Limited Evaluation Budgets

DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts

Deliberation in Latent Space via Differentiable Cache Augmentation

Demonstration Selection for In-Context Learning via Reinforcement Learning

Demystifying Singular Defects in Large Language Models

Dendritic Localized Learning: Toward Biologically Plausible Algorithm

Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning

Density Ratio Estimation with Conditional Probability Paths

Dequantified Diffusion Schrödinger Bridge for Density Ratio Estimation

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective

Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap

Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMs

Differentially Private Boxplots

Differentially Private Federated $k$-Means Clustering with Server-Side Data

Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model

Diffusion Counterfactual Generation with Semantic Abduction

Diffusion on language model encodings for protein sequence generation

Diffusion Sampling Correction via Approximately 10 Parameters

Dimension-Free Adaptive Subgradient Methods with Frequent Directions

Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models

Directly Forecasting Belief for Reinforcement Learning with Delays

Direct Motion Models for Assessing Generated Videos

Discovering a Zero (Zero-Vector Class of Machine Learning)

Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning

Discovering Spoofing Attempts on Language Model Watermarks

Distilling the Knowledge in Data Pruning

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Distributed Event-Based Learning via ADMM

Distributionally Robust Active Learning for Gaussian Process Regression

Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering

Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis

Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective

DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model

DragSolver: A Multi-Scale Transformer for Real-World Automotive Drag Coefficient Estimation

Dynamical phases of short-term memory mechanisms in RNNs

Dynamic Similarity Graph Construction with Kernel Density Estimation

DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making

Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation

EEG-Language Pretraining for Highly Label-Efficient Pathology Detection

Efficient Federated Incomplete Multi-View Clustering

Efficient Quantification of Multimodal Interaction at Sample Level

Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models

Emulating Complex Coastal Processes with Transformers: A Decade-Long High-Resolution Dataset and Preliminary Results

ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks

Energy-Based Flow Matching for Generating 3D Molecular Structure

Enhancing Certified Robustness via Block Reflector Orthogonal Layers

Enhancing Cross-Layer Information Flow in Transformers with Multiway Dynamic Dense Connections

Enhancing Decision-Making of Large Language Models via Actor-Critic

Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization

Enhancing Performance of Explainable AI Models with Constrained Concept Refinement

Enhancing Target-unspecific Tasks through a Features Matrix

Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective

ENSUR: Equitable and Statistically Unbiased Recommendation

EpiCoder: Encompassing Diversity and Complexity in Code Generation

Equivariant Neural Tangent Kernels

Equivariant Polynomial Functional Networks

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling

ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans

Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects

Explaining the role of Intrinsic Dimensionality in Adversarial Training

Explicit Discovery of Nonlinear Symmetries from Dynamic Data

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

Exploring Criteria for Enhanced Loss Reweighting in Large Language Model Unlearning

ExtPose: Robust and Coherent Pose Estimation with Expanding ViT

Falsification of Unconfoundedness by Testing Independence of Causal Mechanisms

Faster Rates for Private Adversarial Bandits

Feature Importance Metrics in the Presence of Missing Data

Features are fate: a theory of transfer learning in high-dimensional regression

FedBEns: One-Shot Federated Learning based on Bayesian Ensemble

FedECADO: A Dynamical System Model of Federated Learning

Few-shot Species Range Estimation

Finding Bipartite-like Clusters on the Fly

Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function

FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials

Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation

Flexibility-conditioned protein structure design with flow matching

Flexible and Efficient Grammar-Constrained Decoding

FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields

Flow Matching for Few-Trial Neural Adaptation with Stable Latent Dynamics

Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices

Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning

From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control

Fully Heteroscedastic Count Regression with Deep Double Poisson Networks

GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks

Generalized Random Forests Using Fixed-Point Trees

Generation from Noisy Examples

Generative Human Trajectory Recovery via Embedding-Space Conditional Diffusion

Generative Intervention Models for Causal Perturbation Modeling

GenMol: A Drug Discovery Generalist with Discrete Diffusion

Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates

Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization

Global-Local Dirichlet Processes for Clustering Grouped Data in the Presence of Group-Specific Idiosyncratic Variables

GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction

Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes

Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs

Gradient Inversion of Multi-Modal Models

GRAM: A Generative Foundation Reward Model for Reward Generalization

Graph Adaptive Autoregressive Moving Average Models

Graph-based Algorithms for Diverse Similarity Search

GSM-$\infty$: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics

Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking

Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update

Hessian Geometry of Latent Space in Generative Models

Heterogeneous Sufficient Dimension Reduction and Subspace Clustering

Hierarchical Graph Tokenization for Molecule-Language Alignment

Hierarchical Overlapping Clustering on Graphs: Cost Function, Algorithm and Scalability

Highly Compressed Tokenizer Can Generate Without Training

High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions

How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction

How to Evaluate and Mitigate IP Infringement in Visual Generative AI?

How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies

How transformers learn structured data: insights from hierarchical filtering

Human-Aligned Image Models Improve Visual Decoding from the Brain

Human Cognition-Inspired Hierarchical Fuzzy Learning Machine

Hybrid Quantum-Classical Multi-Agent Pathfinding

HyperNear: Unnoticeable Node Injection Attacks on Hypergraph Neural Networks

Hypothesis Testing for Generalized Thurstone Models

Identifying neural dynamics using interventional state space models

Importance Sampling for Nonlinear Models

Improved Off-policy Reinforcement Learning in Biological Sequence Design

Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization

Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint

Improving Compositional Generation with Diffusion Models Using Lift Scores

Improving Conversational Capabilities of Speech Language Models via Generative Dual-channel Spoken Dialogue Learning

Improving Flow Matching by Aligning Flow Divergence

Improving Generalization with Flat Hilbert Bayesian Inference

Improving Out-of-Distribution Detection with Markov Logic Networks

Improving Robustness to Subpopulation Shifts by Heuristic Subspace Exploration with Enhanced Diversification

Improving Soft Unification with Knowledge Graph Embedding Methods

Improving Value Estimation Critically Enhances Vanilla Policy Gradient

In-Context Adaptation to Concept Drift for Learned Database Operations

Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations

Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting

Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms

Instruct2See: Learning to Remove Any Obstructions Across Distributions

Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities

Interpreting CLIP with Hierarchical Sparse Autoencoders

Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

Joint Learning of Energy-based Models and their Partition Function

Joint Localization and Activation Editing for Low-Resource Fine-Tuning

Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient

Joker: Joint Optimization Framework for Lightweight Kernel Machines

KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies

Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models

KernelBench: Can LLMs Write Efficient GPU Kernels?

Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization

LADA: Scalable Label-Specific CLIP Adapter for Continual Learning

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

Larger or Smaller Reward Margins to Select Preferences for Alignment?

LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence

Latent Action Learning Requires Supervision in the Presence of Distractors

Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes

LAuReL: Learned Augmented Residual Layer

Learnable Spatial-Temporal Positional Encoding for Link Prediction

Learning-augmented algorithms for MTS with bandit access to multiple predictors

Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction

Learning Curves of Stochastic Gradient Descent in Kernel Regression

Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning

Learning Global and Local Features in Pretrained Remote Sensing Models

Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback

Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models

Learning Likelihood-Free Reference Priors

Learning Mean Field Control on Sparse Graphs

Learning Mixtures of Experts with EM: A Mirror Descent Perspective

Learning Representations of Instruments for Partial Identification of Treatment Effects

Learning Robust Neural Processes with Risk-Averse Stochastic Optimization

Learning Single Index Models with Diffusion Priors

Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

Learning with Exact Invariances in Polynomial Time

Learning With Multi-Group Guarantees For Clusterable Subpopulations

Leveraging Per-Instance Privacy for Machine Unlearning

Linear Bandits with Partially Observable Features

LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification

LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

Logarithmic Regret for Online KL-Regularized Reinforcement Learning

Logits are All We Need to Adapt Closed Models

LOGO --- Long cOntext aliGnment via efficient preference Optimization

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Looking Beyond the Top-1: Transformers Determine Top Tokens in Order

Loss Functions and Operators Generated by f-Divergences

LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models

Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces

Making AutoEncoders Diffusable Again

MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving

MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

Maximum Entropy Reinforcement Learning with Diffusion Policy

Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization

Meta-Black-Box-Optimization through Offline Q-function Learning

Meta Optimality for Demographic Parity Constrained Regression via Post-Processing

MIB: A Mechanistic Interpretability Benchmark

MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data

MindCustomer: Multi-Context Image Generation Blended with Brain Signal

Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers

Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback

Minimum width for universal approximation using squashable activation functions

MiraGe: Editable 2D Images using Gaussian Splatting

Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?

Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries

MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES

Mixed-curvature decision trees and random forests

Mixture of Experts Made Intrinsically Interpretable

Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning

Model Immunization from a Condition Number Perspective

Modified K-means Method with Local Optimality Guarantees

MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding

MoH: Multi-Head Attention as Mixture-of-Head Attention

Multi-Modal Object Re-identification via Sparse Mixture-of-Experts

Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints

Multivariate Conformal Selection

MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners

Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain Transfer

Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning

Nearly Optimal Sample Complexity for Learning with Label Proportions

Near Optimal Non-asymptotic Sample Complexity of 1-Identification

NegMerge: Sign-Consensual Weight Merging for Machine Unlearning

NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare Analytics

Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?

Neural Graph Pattern Machine

Neutral residues: revisiting adapters for model extension

NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits

Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation

Nonparametric Modern Hopfield Models

No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers

NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel

Objective drives the consistency of representational similarity across datasets

Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents

O-MAPLE: Offline Multi-agent Preference Learning

OMNIBAL: TOWARDS FAST INSTRUCT-TUNING FOR VISION-LANGUAGE MODELS VIA OMNIVERSE COMPUTATION BALANCE

One-Pass Feature Evolvable Learning with Theoretical Guarantees

On the Adversarial Robustness of Multi-Kernel Clustering

On the Generalization Ability of Next-Token-Prediction Pretraining

On the Importance of Embedding Norms in Self-Supervised Learning

On the Importance of Gaussianizing Representations

On the Private Estimation of Smooth Transport Maps

On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning

On Volume Minimization in Conformal Regression

On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation

Optimizing Large Language Model Training Using FP4 Quantization

Optimizing Multi-Agent Reasoning through Incomplete Information and Consensus

Optimizing Test-Time Compute via Meta Reinforcement Finetuning

Orient Anything

Origin Identification for Text-Guided Image-to-Image Diffusion Models

Otter: Generating Tests from Issues to Validate SWE Patches

Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner

Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling

Pareto-Optimal Fronts for Benchmarking Symbolic Regression Algorithms

PF3plat: Learning Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis

Phase transitions for the existence of unregularized M-estimators in single index models

Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification

PICI: Efficient Position-Independent Context Caching for Serving Large Language Models

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

Pixel-level Certified Explanations via Randomized Smoothing

Policy Gradient with Tree Expansion

Position: Build Agent Advocates, Not Platform Agents

Position: Deep Learning is Not So Mysterious or Different

Position: Explainable AI Cannot Advance Without Better User Studies

Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks

Position: Humanity Faces Existential Risk from Gradual Disempowerment

Position: LLM Social Simulations Are a Promising Research Method

Position: Stop treating `AGI' as the north-star goal of AI research

Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States

Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process

Position: The Right to AI

Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning

PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design

Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves

Predicting the Susceptibility of Examples to Catastrophic Forgetting

Prediction-Powered Adaptive Shrinkage Estimation

Predictive Data Selection: The Data That Predicts Is the Data That Teaches

Pre-training Auto-regressive Robotic Models with 4D Representations

PRIME: Deep Imbalanced Regression with Proxies

Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty

Probabilistic Verification of Neural Networks using Branch and Bound

Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF

Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models

Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models

PRUNING For GNNs: HIGHER EXPRESSIVENESS, LOWER COMPLEXITY

Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

Quantum Speedup for Hypergraph Sparsification

QuEST: Quantized Gradient Estimation for Accurate Training of Extremely Low-Bitwith Large Language Models

QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval

Radio: Rate–Distortion Optimization for Large Language Model Compression

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

Random Feature Representation Boosting

Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity

Rank-One Modified Value Iteration

Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization

Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment

Reinforcement Learning for Quantum Control under Physical Constraints

Reinforcement learning with random time horizons

RelGNN: Composite Message Passing for Relational Deep Learning

Rényi Neural Processes

RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts

RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

Representative Ranking for Deliberation in the Public Sphere

ResearchTown: Simulator of Human Research Community

ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals

Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation

Rethinking Chain-of-Thought from the Perspective of Self-Training

Rethinking Score Distilling Sampling for 3D Editing and Generation

Rethinking the Temperature for Federated Heterogeneous Distillation

Rethinking Time Encoding via Learnable Transformation Functions

Retrieval Augmented Time Series Forecasting

ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks

Reward-Guided Refinement in Diffusion Models With Applications to Protein and DNA Design

Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks

Risk and cross validation in ridge regression with correlated samples

Robust Automatic Modulation Classification with Fuzzy Regularization

Robust ML Auditing using Prior Knowledge

Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability

RUN: Reversible Unfolding Network for Concealed Object Segmentation

S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Sample-Optimal Agnostic Boosting with Unlabeled Data

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification

SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning

Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation

Scalable Sobolev IPM for Probability Measures on a Graph

Scaling Laws for Upcycling Mixture-of-Experts Language Models

Scaling Probabilistic Circuits via Monarch Matrices

Scaling Trends in Language Model Robustness

Score Matching with Missing Data

scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data

SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations

Selective Preference Aggregation

Self-Organizing Visual Prototypes for Non-Parametric Representation Learning

Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum

Set Valued Predictions For Robust Domain Generalization

Shifting time: Time-series forecasting with Khatri-Rao neural operators

Should Decision-Makers Reveal the Classifiers in Online Strategic Classification?

Simple Randomized Rounding for Max-Min Eigenvalue Augmentation

Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery

SING: Spatial Context in Large Language Model for Next-Gen Wearables

SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting

Sleeping Reinforcement Learning

Soft Diffusion Actor-Critic: Efficient Online Reinforcement Learning for Diffusion Policy

softmax is not enough (for sharp size generalisation)

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

SPD: Sync-Point Drop for efficient tensor parallelism of Large Language Models

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation

SPEX: Scaling Feature Interaction Explanations for LLMs

Spherical Rotation Dimension Reduction with Geometric Loss Functions

SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution

SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images

Stabilizing Sample Similarity in Representation via Mitigating Random Consistency

STAIR: Improving Safety Alignment with Introspective Reasoning

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise

Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning

Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence

Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes

Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups

Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models

Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability

System-Aware Unlearning Algorithms: Use Lesser, Forget Faster

TabFlex: Scaling Tabular Learning to Millions with Linear Attention

Targeted Low-rank Refinement: Enhancing Sparse Language Model with Precision

Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks

TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion

Tensorized Multi-View Multi-Label Classification via Laplace Tensor Rank

Test-Time Adaptation with Binary Feedback

TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph

The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning

The dark side of the forces: assessing non-conservative force models for atomistic machine learning

The Four Color Theorem for Cell Instance Segmentation

The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback

The Lock-in Hypothesis: Stagnation by Algorithm

Theoretical Limitations of Ensembles in the Age of Overparameterization

The Power of Random Features and the Limits of Distribution-Free Gradient Descent

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training

TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting

TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation

Token Coordinated Prompt Attention is Needed for Visual Prompting

ToMA: Token Merging with Attention For Diffusion Models

Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time

Towards Black-Box Membership Inference Attack for Diffusion Models

Towards Robustness and Explainability of Automatic Algorithm Selection

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models

Tractable Transformers for Flexible Conditional Generation

Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra

Training Software Engineering Agents and Verifiers with SWE-Gym

Training Your Agent to Explore via In-Context Adaptation

Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation

Trusted Multi-View Classification with Expert Knowledge Constraints

Trust-Region Twisted Policy Improvement

Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion

Unbiased Recommender Learning from Implicit Feedback via Progressive Proximal Transport

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity

Understanding Model Ensemble in Transferable Adversarial Attack

Understanding the Limits of Deep Tabular Methods with Temporal Shift

UnHiPPO: Uncertainty-aware Initialization for State Space Models

Unifying Specialized Visual Encoders for Video Language Models

Unpaired Point Cloud Completion via Unbalanced Optimal Transport

Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning

Validating Mechanistic Interpretations: An Axiomatic Approach

Variational Control for Guidance in Diffusion Models

Variational Phylogenetic Inference with Products over Bipartitions

Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible

VinePPO: Refining Credit Assignment in RL Training of LLMs

Vintix: Action Model via In-Context Reinforcement Learning

Volume Optimality in Conformal Prediction with Structured Prediction Sets

Watch Out Your Album! On Unintentional Privacy Memorization in Multi-Modal Large Language Models

WATCH: Weighted Adaptive Testing for Changepoint Hypotheses via Weighted Conformal Martingales

When do neural networks learn world models?

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

World models are necessary for zero-shot generalization in agents

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

Zebra: In-Context Generative Pretraining for Solving Parametric PDEs

(ends 1:30 PM)

1 p.m.

Break:

Hosted Grab and Go Lunch

(ends 2:00 PM)

2 p.m.

Invited Talk:

Invited Talk - Andreas Krause

Andreas Krause

(ends 3:00 PM)

3:30 p.m.

Oral 6A Applications in Agents and Coding [3:30-4:30]

Orals 3:30-4:30

[3:30] EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

[3:45] SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

[4:00] CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction

[4:15] ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

(ends 4:30 PM)

Oral 6B Deep Learning Architectures [3:30-4:30]

Orals 3:30-4:30

[3:30] Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG

[3:45] AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization

[4:00] Normalizing Flows are Capable Generative Models

[4:15] In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval

(ends 4:30 PM)

Oral 6C Learning Dynamics 2 [3:30-4:30]

Orals 3:30-4:30

[3:30] Learning dynamics in linear recurrent neural networks

[3:45] LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)

[4:00] LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

[4:15] Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent

(ends 4:30 PM)

Oral 6D Evaluation [3:30-4:30]

Orals 3:30-4:30

[3:30] On Path to Multimodal Generalist: General-Level and General-Bench

[3:45] What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark of Essential Virtual Agent Capabilities

[4:00] How Do Large Language Monkeys Get Their Power (Laws)?

[4:15] Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings

(ends 4:30 PM)

Oral 6E Social and Economic Perspectives [3:30-4:30]

Orals 3:30-4:30

[3:30] The Value of Prediction in Identifying the Worst-Off

[3:45] Generative Social Choice: The Next Generation

[4:00] Statistical Collusion by Collectives on Learning Platforms

[4:15] Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All

(ends 4:30 PM)

4:30 p.m.

Break:

Coffee Break

(ends 5:30 PM)

Poster Session 6 [4:30-7:00]

Posters 4:30-7:00

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss

Directed Graph Grammars for Sequence-based Learning

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Geometric Median (GM) Matching for Robust $k$-Subset Selection from Noisy Data

Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models

M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework

Observation Interference in Partially Observable Assistance Games

Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces

Towards flexible perception with visual memory

Accelerating Large Language Model Reasoning via Speculative Search

A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle

Action Dubber: Timing Audible Actions via Inflectional Flow

Active Evaluation Acquisition for Efficient LLM Benchmarking

Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization

Ad Hoc Teamwork via Offline Goal-Based Decision Transformers

Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

Advective Diffusion Transformers for Topological Generalization

Adversarial Combinatorial Semi-bandits with Graph Feedback

Adversarial Inputs for Linear Algebra Backends

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

AffinityFlow: Guided Flows for Antibody Affinity Maturation

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings

A Lens into Interpretable Transformer Mistakes via Semantic Dependency

Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models

ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling

AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization

Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search

A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver

An All-Atom Generative Model for Designing Protein Complexes

AnalogGenie-Lite: Enhancing Scalability and Precision in Circuit Topology Discovery through Lightweight Graph Modeling

An Automated Graph Foundation Model with Adaptive Graph Neural Architecture Customization

An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability

An End-to-End Model For Logits Based Large Language Models Watermarking

An Error Analysis of Flow Matching for Deep Generative Modeling

A New Approach to Backtracking Counterfactual Explanations: A Causal Framework for Efficient Model Interpretability

A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning

Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions

A Non-isotropic Time Series Diffusion Model with Moving Average Transitions

An Online Learning Approach to Prompt-based Selection of Generative Models

A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

AutoAL: Automated Active Learning with Differentiable Query Strategy Search

Autoencoder-Based Hybrid Replay for Class-Incremental Learning

Automated Hypothesis Validation with Agentic Sequential Falsifications

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

Bayesian Active Learning for Bivariate Causal Discovery

Behavior-agnostic Task Inference for Robust Offline In-context Reinforcement Learning

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety

Beyond Limited Data: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving

BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly

BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution

Bivariate Causal Discovery with Proxy Variables: Integral Solving and Beyond

Boosting Performance on ARC is a Matter of Perspective

B-score: Detecting biases in large language models using response history

BSLoRA: Enhancing the Parameter Efficiency of LoRA with Intra-Layer and Inter-Layer Sharing

C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation

CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging

CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing

Calibrated Physics-Informed Uncertainty Quantification.

Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation

Causal Abstraction Learning based on the Semantic Embedding Principle

CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation

Circumventing Backdoor Space via Weight Symmetry

Clustering Properties of Self-Supervised Learning

CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale

CoDy: Counterfactual Explainers for Dynamic Graphs

CoMemo: LVLMs need image context with image memory

Competitively Consistent Clustering

Compositional Causal Reasoning Evaluation in Language Models

Compositional Condition Question Answering in Tabular Understanding

Compositional Generalization Requires More Than Disentangled Representations

Compositional Generative Multiphysics and Multi-component Simulation

Compositional Scene Understanding through Inverse Generative Modeling

Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration

Conformal Prediction with Cellwise Outliers: A Detect-then-Impute Approach

Conformal Tail Risk Control for Large Language Model Alignment

Confounder-Free Continual Learning via Recursive Feature Normalization

Conservative Offline Goal-Conditioned Implicit V-Learning

ConText: Driving In-context Learning for Text Removal and Segmentation

Contextually Tokenizing Action Sequences for Generative Recommendation

Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective

Continuous Visual Autoregressive Generation via Score Maximization

Contour Integration Underlies Human-Like Vision

Contrastive Localized Language-Image Pre-Training

Controllable Data Generation with Hierarchical Neural Representations

Controlling Large Language Model with Latent Action

Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation

Counterfactual Graphical Models: Constraints and Inference

Covered Forest: Fine-grained generalization analysis of graph neural networks

Critical Iterative Denoising: A Discrete Generative Model Applied to Graphs

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities

Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models

De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks

Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization

Decomposition of Graphic Design with Large Multimodal Model

Deep Bayesian Filter for Bayes-Faithful Data Assimilation

DeepLayout: Learning Neural Representations of Circuit Placement Layout

Deep Neural Cellular Potts Models

Deep Reinforcement Learning from Hierarchical Preference Design

Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph

Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs

Demystifying Long Chain-of-Thought Reasoning

Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling

DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples

Differentiable Solver Search for Fast Diffusion Sampling

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy

Distillation of Discrete Diffusion through Dimensional Correlations

Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning

Diverging Preferences: When do Annotators Disagree and do Models Know?

DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis

DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning

DocVXQA: Context-Aware Visual Explanations for Document Question Answering

Don't Restart, Just Reuse: Reoptimizing MILPs with Dynamic Parameters

Do Vision-Language Models Really Understand Visual Language?

DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers

EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification

Earley-Driven Dynamic Pruning for Efficient Structured Decoding

Effective and Efficient Masked Image Generation Models

Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs

Efficient Bisection Projection to Ensure Neural-Network Feasibility for Optimization over General Set

Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment

Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Efficient Multi-modal Long Context Learning for Training-free Adaptation

Efficient Network Automatic Relevance Determination

Eliciting Language Model Behaviors with Investigator Agents

ELoRA: Low-Rank Adaptation for Equivariant GNNs

Elucidating the design space of language models for image generation

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Enabling Optimal Decisions in Rehearsal Learning under CARE Condition

End-to-End Machine-Learning Framework for Solving Non-Markovian Optimal Control

Enhancing Visual Localization with Cross-Domain Image Generation

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition

EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration

EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions

Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence

ExLM: Rethinking the Impact of $\texttt{[MASK]}$ Tokens in Masked Language Models

Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization

Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs

Extreme Value Policy Optimization for Safe Reinforcement Learning

Falcon: Fast visuomotor policy via partial denoising

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments

Fast Exact Unlearning of Fine-Tuning Data for LLMs

Fast Video Generation with Sliding Tile Attention

FCL: A Function Calling Leaderboard for Large Language Models

FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation

FedClean: A General Robust Label Noise Correction for Federated Learning

Federated Causal Structure Learning with Non-identical Variable Sets

Federated Node-Level Clustering Network with Corss-Subgraph Link Mending

FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation

FG-CLIP: Fine-Grained Visual and Textual Alignment

FIC-TSC: Learning Time Series Classification with Fisher Information Constraint

Fixed-Confidence Multiple Change Point Identification under Bandit Feedback

Flow Matching for Denoised Social Recommendation

FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models

FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making

FrameBridge: Improving Image-to-Video Generation with Bridge Models

From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models

From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers

From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining

From Uncertain to Safe: Conformal Fine-Tuning of Diffusion Models for Safe PDE Control

FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting

Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities

FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks

GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models

Gaussian Mixture Flow Matching Models

Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks

Generalization in Federated Learning: A Conditional Mutual Information Framework

Generalized Category Discovery via Reciprocal Learning and Class-wise Distribution Regularization

Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level

Generalizing Treatment Effects from Randomized Controlled Trials across Environments

Generative Social Choice: The Next Generation

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation

Global Context-aware Representation Learning for Spatially Resolved Transcriptomics

Global Optimization with A Power-Transformed Objective and Gaussian Smoothing

GPEN: Global Position Encoding Network for Enhanced Subgraph Representation Learning

GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning

Gradient Aligned Regression via Pairwise Losses

GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning

Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs

Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning

Graph Generative Pre-trained Transformer

GraphGPT: Generative Pre-trained Graph Eulerian Transformer

Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization

Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs

Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent Distributions

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin

HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation

Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots

High-Dimensional Tensor Regression With Oracle Properties

History-Guided Video Diffusion

Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space

How Do Large Language Monkeys Get Their Power (Laws)?

How Do Transformers Learn Variable Binding?

How Effective Can Dropout Be in Multiple Instance Learning ?

H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models

Human Body Restoration with One-Step Diffusion Model and A New Benchmark

Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning

Hyperbolic Graph Transformer for Collaborative Filtering

Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning

HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking

Hypo3D: Exploring Hypothetical Reasoning in 3D

Imagine While Reasoning in Space: Multimodal Visualization-of-Thought

Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks

Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent

Improved and Oracle-Efficient Online $\ell_1$-Multicalibration

Improved Approximations for Hard Graph Problems using Predictions

Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization

Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens

Improving LLM Video Understanding with 16 Frames Per Second

Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques

Improving Multimodal Learning Balance and Sufficiency through Data Remixing

Improving Out-of-Distribution Detection via Dynamic Covariance Calibration

Improving Reward Model Generalization from Adversarial Process Enhanced Preferences

Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games

In-context denoising with one-layer transformers: connections between attention and associative memory retrieval

In-Context Linear Regression Demystified: Training Dynamics and Expressive Power of Multi-Head Softmax Attention

InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory

InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective

Interpreting the repeated token phenomenon in LLMs

IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models

Introducing 3D Representation for Medical Image Volume-to-Volume Translation via Score Fusion

Inverse Flow and Consistency Models

IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models

Is Noise Conditioning Necessary for Denoising Generative Models?

IT-Bench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

Iterative Refined Transformer for Curriculum Learning Guided De Novo Peptide Sequencing

ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset

Janus: Dual-server Multi-Round Secure Aggregation with Verifiability for Federated Learning

KAN-AD: Time Series Anomaly Detection with Kolmogorov–Arnold Networks

Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage

KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

Language Model as Implicit Tree Search

Large Continual Instruction Assistant

Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems

La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation

Latent Variable Causal Discovery under Selection Bias

Layer-wise Quantization for Quantized Optimistic Dual Averaging

L-Diffusion: Laplace Diffusion for Efficient Pathology Image Segmentation

Learning Adversarial MDPs with Stochastic Hard Constraints

Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization

Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response

Learning Cascade Ranking as One Network

Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification

Learning dynamics in linear recurrent neural networks

Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures

Learning Efficient Robotic Garment Manipulation with Standardization

Learning from Sample Stability for Deep Clustering

Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network

Learning from True-False Labels via Multi-modal Prompt Retrieving

Learning Safe Control via On-the-Fly Bandit Exploration

Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge

Learning to Reuse Policies in State Evolvable Environments

Learnware Specification via Dual Alignment

Let LLM Tell What to Prune and How Much to Prune

LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos

Linear $Q$-Learning Does Not Diverge: Convergence Rates to a Bounded Set

Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting

LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination

LLMScan: Causal Scan for LLM Misbehavior Detection

LLMs Can Plan Faster Only If We Let Them

LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)

Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization

Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers

LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits

Low-Rank Adapting Models for Sparse Autoencoders

M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality

MARS: Unleashing the Power of Variance Reduction for Training Large Models

MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems

Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More

MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation

Matchmaker: Self-Improving Compositional LLM Programs for Schema Matching

Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures

Measuring In-Context Computation Complexity via Hidden State Prediction

Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective

Measuring Variable Importance in Heterogeneous Treatment Effects with Confidence

Memory Layers at Scale

Merging Multiple Models under Permutation Symmetries

M+: Extending MemoryLLM with Scalable Long-Term Memory

MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

Minerva: A Programmable Memory Test Benchmark for Language Models

MissScore: High-Order Score Estimation in the Presence of Missing Data

Mixture of Hidden-Dimensions: Not All Hidden-States’ Dimensions are Needed in Transformer

ML$^2$-GCL: Manifold Learning Inspired Lightweight Graph Contrastive Learning

MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

Models of Heavy-Tailed Mechanistic Universality

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking

Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design

MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles

MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment

MSR-ViR: Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering

Multimodal Medical Code Tokenizer

Multiobjective distribution matching

Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization

Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling

Nested Expectations with Kernel Quadrature

Neural Combinatorial Optimization via Preference Optimization

Neural Encoding and Decoding at Scale

Neural Solver Selection for Combinatorial Optimization

No Free Lunch from Random Feature Ensembles

Noisy SIGNSGD Is More Differentially Private Than You (Might) Think

Non-Asymptotic Length Generalization

Normalizing Flows are Capable Generative Models

OCN: Learning Object-centric Representations for Unsupervised Multi-object Segmentation

Offline Model-based Optimization for Real-World Molecular Discovery

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation

One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation

One-dimensional Path Convolution

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

Online Clustering of Dueling Bandits

Online differential private conformal prediction for uncertainty quantification

On Teacher Hacking in Language Model Distillation

On the Benefits of Active Data Collection in Operator Learning

On the Diversity of Adversarial Ensemble Learning

On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning

On the Guidance of Flow Matching

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training

On the Role of Label Noise in the Feature Learning Process

Open the Eyes of MPNN: Vision Enhances MPNN in Link Prediction

OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning

Optimal Sensor Scheduling for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics

Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Convergence Guarantees

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning

Oscillation-Reduced MXFP4 Training for Vision Transformers

Overcoming Non-monotonicity in Transducer-based Streaming Generation

Overtrained Language Models Are Harder to Fine-Tune

OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models

P(all-atom) Is Unlocking New Path For Protein Design

Parallel Simulation for Sampling under Isoperimetry and Score-based Diffusion Models

Parametric Scaling Law of Tuning Bias in Conformal Prediction

PatchPilot: A Stable and Cost-Efficient Agentic Patching Framework

PENCIL: Long Thoughts with Short Memory

Perception in Reflection

Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models

PHYSICS-INFORMED WEAKLY SUPERVISED LEARNING FOR INTERATOMIC POTENTIALS

PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities

Plan-and-Act: Structured Execution of LLM Agents for Long-Horizon Web Tasks

Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion

Point Cloud Dataset Distillation

PokeChamp: an Expert-level Minimax Language Agent for Competitive Pokemon

Policy Guided Tree Search for Enhanced LLM Reasoning

POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval

Positional encoding meets persistent homology on graphs

Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints

Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning

Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)

Position: You Can't Manufacture a NeRF

Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization

Preference Optimization for Combinatorial Optimization Problems

Preserving AUC Fairness in Learning with Noisy Protected Groups

Pre-Trained Vision-Language Model Selection and Reuse for Downstream Tasks

Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All

Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning

Procurement Auctions via Approximately Optimal Submodular Optimization

Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale

PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering

Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing

Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead

PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment

QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration

Quantum Algorithms for Finite-horizon Markov Decision Processes

Random Policy Evaluation Uncovers Policies of Generative Flow Networks

Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures

Reducing Tool Hallucination via Reliability Alignment

R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models

Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks

Reflection-Bench: Evaluating Agency in Large Language Models

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local Measurements

Reinforcement Learning with Segment Feedback

Rejecting Hallucinated State Targets during Planning

Relaxing the Equivariance Constraint for 3D Molecule Generation

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

Representation Surgery in Model Merging with Probabilistic Modeling

Representative Language Generation

ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation

Resolving Lexical Bias in Model Editing

Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning

Rethinking Latent Representations in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation

Rethink the Role of Deep Learning towards Large-scale Quantum Systems

Retraining-free Merging of Sparse Mixture-of-Experts via Hierarchical Clustering

Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG

Revisiting Convergence: A Study on Shuffling-Type Gradient Methods

Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

Reward-free World Models for Online Imitation Learning

Reward Modeling with Ordinal Feedback: Wisdom of the Crowd

Reward Translation via Reward Machine in Semi-Alignable MDPs

Robust Autonomy Emerges from Self-Play

Robust Multi-Agent Reinforcement Learning with Stochastic Adversary

Robust Multimodal Large Language Models Against Modality Conflicts

Robust Sparsification via Sensitivity

Robust Spatio-Temporal Centralized Interaction for OOD Learning

ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck

RULEBREAKERS: Challenging Large Language Models at the Crossroads between Formal Logic and Human-like Reasoning

Runtime Analysis of Evolutionary NAS for Multiclass Classification

SAE-V: Interpreting Multimodal Models for Enhanced Alignment

Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism Design

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

Sampling from Binary Quadratic Distributions via Stochastic Localization

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Scalable Model Merging with Progressive Layer-wise Distillation

Scaling Laws for Differentially Private Language Models

Schwarz–Schur Involution and Dirichlet-to-Neumann Condensing: Partial Differential Equations and Sparse Linear Systems Solved 1000x Faster

sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models

Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport

SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding

Self-Bootstrapping for Versatile Test-Time Adaptation

Self-Consuming Generative Models with Adversarially Curated Data

Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation

Self-supervised Heterogeneous Graph Neural Network with Optimal Transport

Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images

Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning

Simple Policy Optimization

Simplicity Bias and Optimization Threshold in Two-Layer Networks

Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation

Slimming the Fat-Tail: MoF for Adaptive Time Series Modeling

Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration

Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo

SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model

Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks

SPD: Smoothed Primal-Dual Methods for Nonconvex Optimization with Equilibrium Constraints

SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs

Specialization-generalization transition in exemplar-based in-context learning

Speeding up Policy Simulation in Supply Chain RL

SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity

Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization

Stable Fair Graph Representation Learning with Lipschitz Constraint

Statistical Collusion by Collectives on Learning Platforms

Stealix: Model Stealing via Prompt Evolution

SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics

Stream-level Flow Matching with Gaussian Processes

Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM

Structure-informed Risk Minimization for Robust Ensemble Learning

Suitability Filter: A Statistical Framework for Model Evaluation in Real-World Deployment Settings

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems

Tackling View-Dependent Semantics in 3D Language Gaussian Splatting

TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut Optimization

Targeted control of fast prototyping through domain-specific interface

Task Generalization With AutoRegressive Compositional Structure

Teaching Language Models to Critique via Reinforcement Learning

TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching

Testing Conditional Mean Independence Using Generative Neural Networks

Test-time Adapted Reinforcement Learning with Action Entropy Regularization

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions

The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)

Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport

The Value of Prediction in Identifying the Worst-Off

Thickness-aware E(3)-Equivariant Mesh Neural Networks

Tight and Fast Bounds for Multi-Label Learning

TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation

TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting

TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

TLLC: Transfer Learning-based Label Completion for Crowdsourcing

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

Towards Escaping from Class Dependency Modeling for Multi-Dimensional Classification

Towards Practical Defect-Focused Automated Code Review

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration

Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift

Towards Trustworthy Distributed Learning with Untrusted Parties

Training Diffusion-based Generative Models with Limited Data

Trajectory Inference with Smooth Schrödinger Bridges

Transfer Learning for Nonparametric Contextual Dynamic Pricing

TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree

Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints

TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models

TruthFlow: Truthful LLM Generation via Representation Flow Correction

TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack

Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models

Understanding Mode Connectivity via Parameter Space Symmetry

Understanding Nonlinear Implicit Bias via Region Counts in Input Space

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods

Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More

Understanding Synthetic Context Extension via Retrieval Heads

Unified Breakdown Analysis for Byzantine Robust Gossip

UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation

Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems

UnitFlow: Synthesizing Software Engineering Data in a Test-Driven Manner

Unlocking the Capabilities of Vision-Language Models for Generalizable Deepfake Detection

Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments

Unsupervised Learning for Class Distribution Mismatch

UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models

Variational Counterfactual Intervention Planning to Achieve Target Outcomes

Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach

WAVE: Weighted Autoregressive Varing Gate for Time Series Forecasting

Weight-Aware Fine-Tuning for Multi-faceted Efficiency across Parameters, Representations, Compute and Memory

Weight matrices compression based on PDB model in deep neural networks

What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning

What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark of Essential Virtual Agent Capabilities

When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need

When Entropy Misleads Policy Optimization

Where is the Truth? The Risk of Getting Confounded in a Continual World

Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg

WILTing Trees: Interpreting the Distance Between MPNN Embeddings

You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption

Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer

ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality

(ends 7:00 PM)

FRI 18 JUL

7:30 a.m.

Registration West

(ends 4:00 PM)

Registration East

(ends 12:00 PM)

8:30 a.m.

Workshop:

Programmatic Representations for Agent Learning

(ends 6:00 PM)

Workshop:

3rd Workshop on High-dimensional Learning Dynamics (HiLD)

(ends 6:00 PM)

Workshop:

2nd Workshop on Models of Human Feedback for AI Alignment (MoFA)

(ends 6:00 PM)

Workshop:

Multi-Agent Systems in the Era of Foundation Models: Opportunities, Challenges and Futures

(ends 6:00 PM)

Workshop:

Machine Unlearning for Generative AI

(ends 6:00 PM)

Workshop:

Tiny Titans: The next wave of On-Device Learning for Foundation Models (TTODLer-FM)

(ends 6:00 PM)

Workshop:

Scaling Up Intervention Models

(ends 6:00 PM)

Workshop:

Machine Learning for Wireless Communication and Networks (ML4Wireless)

(ends 6:00 PM)

Workshop:

Assessing World Models: Methods and Metrics for Evaluating Understanding

(ends 6:00 PM)

Workshop:

2nd Generative AI for Biology Workshop

(ends 6:00 PM)

Workshop:

CODEML: Championing Open-source DEvelopment in Machine Learning

(ends 6:00 PM)

Workshop:

2nd Workshop on Test-Time Adaptation: Putting Updates to the Test (PUT)

(ends 6:00 PM)

Workshop:

ICML 2025 Workshop on Computational Optimization of Buildings (CO-BUILD)

(ends 6:00 PM)

Workshop:

1st Workshop on Foundation Models for Structured Data (FMSD)

(ends 6:00 PM)

Workshop:

2nd AI for Math Workshop @ ICML 2025

(ends 6:00 PM)

Workshop:

The 1st Workshop on Vector Databases

(ends 6:00 PM)

Workshop:

Tokenization Workshop (TokShop)

(ends 6:00 PM)

9 a.m.

Break:

Coffee Break

(ends 10:00 AM)

noon

Break:

Hosted Grab and Go Lunch

(ends 1:00 PM)

3 p.m.

Break:

Coffee Break

(ends 3:30 PM)

SAT 19 JUL

7:30 a.m.

Registration West

(ends 12:00 PM)

8:30 a.m.

Workshop:

TerraBytes: Towards global datasets and models for Earth Observation

(ends 6:00 PM)

Workshop:

DIG-BUGS: Data in Generative Models (The Bad, the Ugly, and the Greats)

(ends 6:00 PM)

Workshop:

Exploration in AI Today (EXAIT)

(ends 6:00 PM)

Workshop:

Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences

(ends 6:00 PM)

Workshop:

Workshop on Computer Use Agents

(ends 6:00 PM)

Workshop:

ICML 2025 Workshop on Collaborative and Federated Agentic Workflows (CFAgentic @ ICML'25)

(ends 6:00 PM)

Workshop:

Actionable Interpretability

(ends 6:00 PM)

Workshop:

Workshop on Technical AI Governance

(ends 6:00 PM)

Workshop:

DataWorld: Unifying data curation frameworks across domains

(ends 6:00 PM)

Workshop:

ES-FoMo III: 3rd Workshop on Efficient Systems for Foundation Models

(ends 6:00 PM)

Workshop:

The Second Workshop on Long-Context Foundation Models

(ends 6:00 PM)

Workshop:

The 2nd Workshop on Reliable and Responsible Foundation Models

(ends 6:00 PM)

Workshop:

AI Heard That! ICML 2025 Workshop on Machine Learning for Audio

(ends 6:00 PM)

Workshop:

Methods and Opportunities at Small Scale (MOSS)

(ends 6:00 PM)

Workshop:

Building Physically Plausible World Models

(ends 6:00 PM)

Workshop:

The Impact of Memorization on Trustworthy Foundation Models

(ends 6:00 PM)

9 a.m.

Break:

Coffee Break

(ends 10:00 AM)

noon

Break:

Hosted Grab and Go Lunch

(ends 1:00 PM)

3 p.m.

Break:

Coffee Break

(ends 3:30 PM)