ICML 2025

3,330 papers

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

lincan Cai, Jingxuan Kang, Shuang Li, Wenxuan Ma, Binhui Xie

Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts

Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim

HyperNear: Unnoticeable Node Injection Attacks on Hypergraph Neural Networks

Tingyi Cai, Yunliang Jiang, Ming Li, Lu Bai, Changqin Huang

GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation

Yi Cai, Thibaud Ardoin, Gerhard Wunder

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

Francesco Cagnetta, Hyunmo Kang, Matthieu Wyart

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

Ju-Seung Byun, Andrew Perrault

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

Undral Byambadalai, Tomu Hirata, Tatsushi Oka, Shota Yasui

Learning Multi-Level Features with Matryoshka Sparse Autoencoders

Bart Bussmann, Noa Nabeshima, Adam Karvonen, Neel Nanda

Where is the Truth? The Risk of Getting Confounded in a Continual World

Florian Peter Busch, Roshni Ramanna Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting

Distillation Scaling Laws

Dan Busbridge, Amitis Shidani, Floris Weers, Jason Ramapuram, Etai Littwin

Nearly Optimal Sample Complexity for Learning with Label Proportions

Róbert István Busa-Fekete, Travis Dick, Claudio Gentile, Haim Kaplan, Tomer Koren

Distributed Differentially Private Data Analytics via Secure Sketching

Jakob Burkhardt, Hannah Keller, Claudio Orlandi, Chris Schwiegelshohn

Accurate and Efficient World Modeling with Masked Latent Transformers

Maxime Burchi, Radu Timofte

Deep Reinforcement Learning from Hierarchical Preference Design

Alexander Bukharin, Yixiao Li, Pengcheng He, Tuo Zhao

Understanding and Improving Length Generalization in Recurrent Models

Ricardo Buitrago, Albert Gu

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

Ngoc Bui, Menglin Yang, Runjin Chen, Leonardo Neves, Mingxuan Ju

O-MAPL: Offline Multi-agent Preference Learning

The Viet Bui, Tien Anh Mai, Thanh Hong Nguyen

Competitively Consistent Clustering

Niv Buchbinder, Roie Levin, Yue Yang

ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation

Tianci Bu, Le Zhou, Wenchuan Yang, Jianhong Mou, Kang Yang

NEAR: Neural Electromagnetic Array Response

Yinyan Bu, Jiajie Yu, Kai Zheng, Xinyu Zhang, Piya Pal

What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities

Wendong Bu, Yang Wu, Qifan Yu, Minghe Gao, Bingchen Miao

Provable In-Context Vector Arithmetic via Retrieving Task Concepts

Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang

Ergodic Generative Flows

Leo Maxime Brunswic, Mateo Clémente, Rui Heng Yang, Adam Sigal, Amir Rasouli

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

Zachary C. Brown, David Carlson

Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs

Greyson Brothers

The Limits of Tractable Marginalization

Oliver Broadrick, Sanyam Agarwal, Guy Van den Broeck, Markus Bläser

Cross-regularization: Adaptive Model Complexity through Validation Gradients

Carlos Stein Brito

E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time

Adam Breuer

Integer Programming for Generalized Causal Bootstrap Designs

Jennifer Rogers Brennan, Sebastien Lahaie, Adel Javanmard, Nick Doudchenko, Jean Pouget-Abadie

Learning-Augmented Hierarchical Clustering

Vladimir braverman, Jon C. Ergun, Chen Wang, Samson Zhou

Relative Error Fair Clustering in the Weak-Strong Oracle Model

Vladimir braverman, Prathamesh Dharangutte, Shaofeng H.-C. Jiang, Hoai-An Nguyen, Chen Wang

DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts

Tobias Braun, Mark Rothermel, Marcus Rohrbach, Anna Rohrbach

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

Lukas Braun, Erin Grant, Andrew M Saxe

Mechanisms of Projective Composition of Diffusion Models

Arwen Bradley, Preetum Nakkiran, David Berthelot, James Thornton, Joshua M. Susskind

BARK: A Fully Bayesian Tree Kernel for Black-box Optimization

Toby Boyne, Jose Pablo Folch, Robert Matthew Lee, Behrang Shafei, Ruth Misener

AutoEval Done Right: Using Synthetic Data for Model Evaluation

Pierre Boyeau, Anastasios Nikolas Angelopoulos, Tianle Li, Nir Yosef, Jitendra Malik

Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks

Etienne Boursier, Nicolas Flammarion

Learning to Match Unpaired Data with Minimum Entropy Coupling

Mustapha BOUNOUA, Giulio Franzese, Pietro Michiardi

Quantifying Treatment Effects: Estimating Risk Ratios via Observational Studies

Ahmed Boughdiri, Julie Josse, Erwan Scornet

On the Query Complexity of Verifier-Assisted Language Generation

Edoardo Botta, Yuchen Li, Aashay Mehta, Jordan T. Ash, Cyril Zhang

Reinforcement Learning with Random Time Horizons

Enric Ribera Borrell, Lorenz Richter, Christof Schuette

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

Ekaterina Borodich, Alexander Gasnikov, Dmitry Kovalev

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks

Valentyn Boreiko, Alexander Panfilov, Václav Voráček, Matthias Hein, Jonas Geiping

How Much Can We Forget about Data Contamination?

Sebastian Bordt, Suraj Srinivas, Valentyn Boreiko, Ulrike Von Luxburg

Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer

Blake Bordelon, Cengiz Pehlevan

Flowing Datasets with Wasserstein over Wasserstein Gradient Flows

Clément Bonet, Christophe Vauthier, Anna Korba

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization

Simone Bombari, Marco Mondelli

Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency

Georg Bökman, David Nordström, Fredrik Kahl

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

Velibor Bojkovic, Xiaofeng Wu, Bin Gu

An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures

Thibaut Boissin, Franck Mamalet, Thomas FEL, Agustin Martin Picard, Thomas Massena

DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra

Montgomery Bohde, Mrunali Manjrekar, Runzhong Wang, Shuiwang Ji, Connor W. Coley

Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation

Yoann Boget

A Variational Perspective on Generative Protein Fitness Optimization

Lea Bogensperger, Dominik Narnhofer, Ahmed Allam, Konrad Schindler, Michael Krauthammer

Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound

David Boetius, Stefan Leue, Tobias Sutter

Generative Social Choice: The Next Generation

Niclas Boehmer, Sara Fish, Ariel D. Procaccia

Physics-Informed Generative Modeling of Wireless Channels

Benedikt Böck, Andreas Oeldemann, Timo Mayer, Francesco Rossetto, Wolfgang Utschick

Point Cloud Dataset Distillation

Deyu Bo, Xinchao Wang

Probably Approximately Global Robustness Certification

Peter Blohm, Patrick Indri, Thomas Gärtner, Sagar Malhotra

GaussMark: A Practical Approach for Structural Watermarking of Language Models

Adam Block, Alexander Rakhlin, Ayush Sekhari

Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification

Jan Blechschmidt, Tom-Christian Riemer, Max Winkler, Martin Stoll, Jan-Frederik Pietschmann

False Coverage Proportion Control for Conformal Prediction

Alexandre Blain, Bertrand Thirion, Pierre Neuvial

Universal Approximation of Mean-Field Models via Transformers

Shiba Biswal, Karthik Elamvazhuthi, Rishi Sonthalia

ENSUR: Equitable and Statistically Unbiased Recommendation

Nitin Bisht, Xiuwen Gong, Guandong Xu

Learning Likelihood-Free Reference Priors

Nicholas George Bishop, Daniel Jarne Ornia, Joel Dyer, Ani Calinescu, Michael J. Wooldridge

The dark side of the forces: assessing non-conservative force models for atomistic machine learning

Filippo Bigi, Marcel F. Langer, Michele Ceriotti

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

Alexander Bienstock, Ujjwal Kumar, Antigoni Polychroniadou

Rethinking Aleatoric and Epistemic Uncertainty

Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope, Mark van der Wilk, Adam Foster

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

Aviv Bick, Eric Xing, Albert Gu

Scaling Inference-Efficient Language Models

Song Bian, Minghao Yan, Shivaram Venkataraman

IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

Tian Bian, Yifan Niu, Chaohao Yuan, Chengzhi Piao, Bingzhe Wu

Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation

Jian Bi, Qianliang Wu, Xiang Li, Shuo Chen, Jianjun Qian

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

Zhenni Bi, Kai Han, Chuanjian Liu, Yehui Tang, Yunhe Wang

Learning multivariate Gaussians with imperfect advice

Arnab Bhattacharyya, Davin Choo, Philips George John, Themis Gouleakis

Almost Optimal Fully Dynamic k-Center Clustering with Recourse

Sayan Bhattacharya, Martín Costa, Ermiya Farokhnejad, Silvio Lattanzi, Nikos Parotsidis

Multi-Objective Causal Bayesian Optimization

Shriya Bhatija, Paul-David Zuercher, Jakob Thumm, Thomas Bohné

AtlasD: Automatic Local Symmetry Discovery

Manu Bhat, Jonghyun Park, Jianke Yang, Nima Dehmamy, Robin Walters

Multiaccuracy and Multicalibration via Proxy Groups

Beepul Bharti, Mary Versa Clemens-Sewall, Paul Yi, Jeremias Sulam

Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving

Ankit Bhardwaj, Amar Phanishayee, Deepak Narayanan, Ryan Stutsman

Highly Compressed Tokenizer Can Generate Without Training

Lukas Lao Beyer, Tianhong Li, Xinlei Chen, Sertac Karaman, Kaiming He

Whitened CLIP as a Likelihood Surrogate of Images and Captions

Roy Betser, Meir Yossef Levi, Guy Gilboa

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley, Daniel Chee Hian Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao

Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection

Louis Béthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, Marco Cuturi

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

Maricela Best Mckay, Avleen Kaur, Chen Greif, Brian Wetton

Geometry-Informed Neural Networks

Arturs Berzins, Andreas Radler, Eric Volkmann, Sebastian Sanokowski, Sepp Hochreiter

Self-Play Q-Learners Can Provably Collude in the Iterated Prisoner’s Dilemma

Quentin Bertrand, Juan Agustin Duque, Emilio Calvano, Gauthier Gidel

Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms

Andrea Bertazzi, Tim Johnston, Gareth O. Roberts, Alain Oliviero Durmus

Modular Duality in Deep Learning

Jeremy Bernstein, Laker Newhouse

Online Learning in the Random-Order Model

Martino Bernasconi, Andrea Celli, Riccardo Colini Baldeschi, Federico Fusco, Stefano Leonardi

No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization

Martino Bernasconi, Matteo Castiglioni, Andrea Celli

Global curvature for second-order optimization of neural networks

Alberto Bernacchia

Memory Layers at Scale

Vincent-Pierre Berges, Barlas Oguz, Daniel Haziza, Wen-tau Yih, Luke Zettlemoyer

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Akhiad Bercovich, Tomer Ronen, Talor Abramovich, Nir Ailon, Nave Assaf

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

Ziyad Benomar, Lorenzo Croissant, Vianney Perchet, Spyros Angelopoulos

Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach

Omar Bennouna, Jiawei Zhang, Saurabh Amin, Asuman E. Ozdaglar

AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting

Abdelhakim Benechehab, Vasilii Feofanov, Giuseppe Paolo, Albert Thomas, Maurizio Filippone

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

Ihab Bendidi, Yassir El Mesbahi, Alisandra Kaye Denton, Karush Suri, Kian Kenyon-Dean

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

Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Théo Bontempelli, Thomas Bouabça

Distilling the Knowledge in Data Pruning

Emanuel Ben Baruch, Adam Botach, Igor Kviatkovsky, Manoj Aggarwal, Gérard Medioni

The Limits of Predicting Agents from Behaviour

Alexis Bellot, Jonathan Richens, Tom Everitt