ICML 2025

3,330 papers

Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation

Kosuke Nakanishi, Akihiro Kubo, Yuji Yasui, Shin Ishii

Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts

Amir Najafi, Samin Mahdizadeh Sani, Farzan Farnia

Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers

Thiziri Nait Saada, Alireza Naderi, Jared Tanner

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

Lakshmi Nair, Ian Trase, J. Mark Kim

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

Srijith Nair, Michael Lin, Peizhong Ju, Amirreza Talebi, Elizabeth Serena Bentley

Matryoshka Quantization

Pranav Ajit Nair, Puranjay Datta, Jeff Dean, Prateek Jain, Aditya Kusupati

DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning

Aaditya Naik, Jason Liu, Claire Wang, Amish Sethi, Saikat Dutta

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

Peer Nagy, Sascha Yves Frey, Kang Li, Bidipta Sarkar, Svitlana Vyetrenko

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

Vaishnavh Nagarajan, Chen Henry Wu, Charles Ding, Aditi Raghunathan

Preference Adaptive and Sequential Text-to-Image Generation

Ofir Nabati, Guy Tennenholtz, ChihWei Hsu, Moonkyung Ryu, Deepak Ramachandran

A Classification View on Meta Learning Bandits

Mirco Mutti, Jeongyeol Kwon, Shie Mannor, Aviv Tamar

LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces

Rashid Mushkani, Shravan Nayak, Hugo Berard, Allison Cohen, Shin Koseki

You Get What You Give: Reciprocally Fair Federated Learning

Aniket Murhekar, Jiaxin Song, Parnian Shahkar, Bhaskar Ray Chaudhury, Ruta Mehta

Fast Exact Unlearning for In-Context Learning Data for LLMs

Andrei Ioan Muresanu, Anvith Thudi, Michael R. Zhang, Nicolas Papernot

A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints

Michael Munn, Susan Wei

Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?

Konrad Mundinger, Max Zimmer, Aldo Kiem, Christoph Spiegel, Sebastian Pokutta

LineFlow: A Framework to Learn Active Control of Production Lines

Kai Müller, Martin Wenzel, Tobias Windisch

Best of Both Worlds: Regret Minimization versus Minimax Play

Adrian Müller, Jon Schneider, Stratis Skoulakis, Luca Viano, Volkan Cevher

Mahalanobis++: Improving OOD Detection via Feature Normalization

Maximilian Müller, Matthias Hein

Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss

Abhijeet Mulgund, Chirag Pabbaraju

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

Sagnik Mukherjee, Abhinav Chinta, Takyoung Kim, Tarun Anoop Sharma, Dilek Hakkani Tur

MIB: A Mechanistic Interpretability Benchmark

Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin

CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries

Ni Mu, Hao Hu, Xiao Hu, Yiqin Yang, Bo Xu

SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression

Mohammad Mozaffari, Amir Yazdanbakhsh, Maryam Mehri Dehnavi

Sparse Autoencoders for Hypothesis Generation

Rajiv Movva, Kenny Peng, Nikhil Garg, Jon Kleinberg, Emma Pierson

GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning

Zhun Mou, bin xia, Zhengchao Huang, Wenming Yang, Jiaya Jia

Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces

Henry Moss, Sebastian W. Ober, Tom Diethe

Geometric Hyena Networks for Large-scale Equivariant Learning

Artem Moskalev, Mangal Prakash, Junjie Xu, Tianyu Cui, Rui Liao

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

Malte Mosbach, Jan Niklas Ewertz, Angel Villar-Corrales, Sven Behnke

Revisiting Non-Acyclic GFlowNets in Discrete Environments

Nikita Morozov, Ian Maksimov, Daniil Tiapkin, Sergey Samsonov

Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel

Carlota Parés Morlans, Michelle Yi, Claire Chen, Sarah A Wu, Rika Antonova

Dimensionality Reduction on Complex Vector Spaces for Euclidean Distance with Dynamic Weights

Simone Moretti, Paolo Pellizzoni, Francesco Silvestri

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

Alexander Moreno, Justin Xiao, Jonathan Mei

Online Episodic Convex Reinforcement Learning

Bianca Marin Moreno, Khaled Eldowa, Pierre Gaillard, Margaux Brégère, Nadia Oudjane

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

Rudy Morel, Jiequn Han, Edouard Oyallon

A Two-Stage Learning-to-Defer Approach for Multi-Task Learning

Yannis Montreuil, Yeo Shu Heng, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi

Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees

Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi

Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity

Alessandro Montenegro, Marco Mussi, Matteo Papini, Alberto Maria Metelli

A Variational Information Theoretic Approach to Out-of-Distribution Detection

Sudeepta Mondal, Zhuolin Jiang, Ganesh Sundaramoorthi

Adversarial Inputs for Linear Algebra Backends

Jonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer

Symmetry-Driven Discovery of Dynamical Variables in Molecular Simulations

Jeet Mohapatra, Nima Dehmamy, Csaba Both, Subhro Das, Tommi Jaakkola

Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning

Mehrdad Moghimi, Hyejin Ku

NoLiMa: Long-Context Evaluation Beyond Literal Matching

Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Trung Bui, Ryan A. Rossi

GMAIL: Generative Modality Alignment for generated Image Learning

Shentong Mo, Sukmin Yun

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

Sarthak Mittal, Eric Elmoznino, Leo Gagnon, Sangnie Bhardwaj, Guillaume Lajoie

Equivariant Neural Tangent Kernels

Philipp Misof, Pan Kessel, Jan E Gerken

SING: Spatial Context in Large Language Model for Next-Gen Wearables

Ayushi Mishra, Yang Bai, Priyadarshan Narayanasamy, Nakul Garg, Nirupam Roy

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Samuel Miserendino, Michele Wang, Tejal Patwardhan, Johannes Heidecke

Measuring Diversity: Axioms and Challenges

Mikhail Mironov, Liudmila Prokhorenkova

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence

Gouki Minegishi, Hiroki Furuta, Shohei Taniguchi, Yusuke Iwasawa, Yutaka Matsuo

Deep Neural Cellular Potts Models

Koen Minartz, Tim D’Hondt, Leon Hillmann, Jörn Starruß, Lutz Brusch

Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs

Hancheng Min, René Vidal

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Rui Min, Tianyu Pang, Chao Du, Qian Liu, Minhao Cheng

Function-Space Learning Rates

Edward Milsom, Ben Anson, Laurence Aitchison

Embedding Safety into RL: A New Take on Trust Region Methods

Nikola Milošević, Johannes Müller, Nico Scherf

Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training

Max Milkert, David Hyde, Forrest John Laine

Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework

Terje Mildner, Oliver Hamelijnck, Paris Giampouras, Theodoros Damoulas

Computing Voting Rules with Improvement Feedback

Evi Micha, Vasilis Varsamis

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

Yuchun Miao, Sen Zhang, Liang Ding, Yuqi Zhang, Lefei Zhang

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

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

Rethinking Score Distilling Sampling for 3D Editing and Generation

Xingyu Miao, Haoran Duan, Yang Long, Jungong Han

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

Zhenxing Mi, Kuan-Chieh Wang, Guocheng Qian, Hanrong Ye, Runtao Liu

On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning

Naram Mhaisen, George Iosifidis

A Bregman Proximal Viewpoint on Neural Operators

Abdel-Rahim Mezidi, Jordan Patracone, Saverio Salzo, Amaury Habrard, Massimiliano Pontil

Benchmarking Quantum Reinforcement Learning

Nico Meyer, Christian Ufrecht, George Yammine, Georgios Kontes, Christopher Mutschler

Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra

Raphael A Meyer, William Joseph Swartworth, David Woodruff

Discovering a Zero (Zero-Vector Class of Machine Learning)

Harikrishna Metta, Venkatesh Babu Radhakrishnan

Diffusion on Language Model Encodings for Protein Sequence Generation

Viacheslav Meshchaninov, Pavel Strashnov, Andrey Shevtsov, Fedor Nikolaev, Nikita Ivanisenko

LAuReL: Learned Augmented Residual Layer

Gaurav Menghani, Ravi Kumar, Sanjiv Kumar

CLOVER: Cross-Layer Orthogonal Vectors Pruning

Fanxu Meng, Pingzhi Tang, Fan Jiang, Muhan Zhang

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

Fanqing Meng, Jiaqi Liao, Xinyu Tan, Quanfeng Lu, Wenqi Shao

TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching

Yue Meng, Chuchu Fan

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

Linjian Meng, Wubing Chen, Wenbin Li, Tianpei Yang, Youzhi Zhang

MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs

Tommaso Mencattini, Robert Adrian Minut, Donato Crisostomi, Andrea Santilli, Emanuele Rodolà

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

Tomer Meir, Uri Shalit, Malka Gorfine

A Generalization Theory for Zero-Shot Prediction

Ronak Mehta, Zaïd Harchaoui

Automatic Differentiation of Optimization Algorithms with Time-Varying Updates

Sheheryar Mehmood, Peter Ochs

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

Matthieu Meeus, Lukas Wutschitz, Santiago Zanella-Beguelin, Shruti Tople, Reza Shokri

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

Marko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li

Return Capping: Sample Efficient CVaR Policy Gradient Optimisation

Harry Mead, Clarissa Costen, Bruno Lacerda, Nick Hawes

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

Paul Mcvay, Sergio Arnaud, Ada Martin, Arjun Majumdar, Krishna Murthy Jatavallabhula

Leveraging Predictive Equivalence in Decision Trees

Hayden McTavish, Zachery Boner, Jon Donnelly, Margo Seltzer, Cynthia Rudin

Polynomial-Time Approximability of Constrained Reinforcement Learning

Jeremy McMahan

Anytime-Constrained Equilibria in Polynomial Time

Jeremy McMahan

Scaling Laws for Differentially Private Language Models

Ryan McKenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles

Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements

Arya Mazumdar, Neha Sangwan

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

Walter Mayor, Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws

Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel

AuPair: Golden Example Pairs for Code Repair

Aditi Mavalankar, Hassan Mansoor, Zita Marinho, Mariia Samsikova, Tom Schaul

Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization

Luca Masserano, Abdul Fatir Ansari, Boran Han, Xiyuan Zhang, Christos Faloutsos

Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks

Thomas Massena, Léo Andéol, Thibaut Boissin, Franck Mamalet, Corentin Friedrich

Provable Length Generalization in Sequence Prediction via Spectral Filtering

Annie Marsden, Evan Dogariu, Naman Agarwal, Xinyi Chen, Daniel Suo

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

Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartłomiej Twardowski, Andrew D. Bagdanov

Transformative or Conservative? Conservation laws for ResNets and Transformers

Sibylle Marcotte, Remi Gribonval, Gabriel Peyré

Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity

Arto Maranjyan, Alexander Tyurin, Peter Richtarik

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

Arto Maranjyan, El Mehdi Saad, Peter Richtarik, Francesco Orabona

Principled Algorithms for Optimizing Generalized Metrics in Binary Classification

Anqi Mao, Mehryar Mohri, Yutao Zhong

Mastering Multiple-Expert Routing: Realizable H-Consistency and Strong Guarantees for Learning to Defer

Anqi Mao, Mehryar Mohri, Yutao Zhong

Hypo3D: Exploring Hypothetical Reasoning in 3D

Ye Mao, Weixun Luo, Junpeng Jing, Anlan Qiu, Krystian Mikolajczyk