ICML 2025

3,330 papers

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

Luca M. Schulze Buschoff, Konstantinos Voudouris, Elif Akata, Matthias Bethge, Joshua B. Tenenbaum

Mastering Board Games by External and Internal Planning with Language Models

John Schultz, Jakub Adamek, Matej Jusup, Marc Lanctot, Michael Kaisers

Adjustment for Confounding using Pre-Trained Representations

Rickmer Schulte, David Rügamer, Thomas Nagler

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

Jan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac, Anderson Schneider, Yuriy Nevmyvaka

Temperature-Annealed Boltzmann Generators

Henrik Schopmans, Pascal Friederich

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity

Mark Schöne, Babak Rahmani, Heiner Kremer, Fabian Falck, Hitesh Ballani

Hyperband-based Bayesian Optimization for Black-box Prompt Selection

Lennart Schneider, Martin Wistuba, Aaron Klein, Jacek Golebiowski, Giovanni Zappella

Generative Intervention Models for Causal Perturbation Modeling

Nora Schneider, Lars Lorch, Niki Kilbertus, Bernhard Schölkopf, Andreas Krause

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Thomas Schmied, Thomas Adler, Vihang Prakash Patil, Maximilian Beck, Korbinian Pöppel

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

Laines Schmalwasser, Niklas Penzel, Joachim Denzler, Julia Niebling

Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

Connor Schenck, Isaac Reid, Mithun George Jacob, Alex Bewley, Joshua Ainslie

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training

Fabian Schaipp, Alexander Hägele, Adrien Taylor, Umut Simsekli, Francis Bach

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

Rylan Schaeffer, Hailey Schoelkopf, Brando Miranda, Gabriel Mukobi, Varun Madan

How Do Large Language Monkeys Get Their Power (Laws)?

Rylan Schaeffer, Joshua Kazdan, John Hughes, Jordan Juravsky, Sara Price

Symmetry-Robust 3D Orientation Estimation

Christopher Scarvelis, David Benhaim, Paul Zhang

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

Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang

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

Eshika Saxena, Alberto Alfarano, Emily Wenger, Kristin E. Lauter

Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization

Hiroshi Sawada, Kazuo Aoyama, Yuya Hikima

NestQuant: nested lattice quantization for matrix products and LLMs

Semyon Savkin, Eitan Porat, Or Ordentlich, Yury Polyanskiy

WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models

Chinmay Savadikar, Xi Song, Tianfu Wu

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations

Davide Sartor, Alberto Sinigaglia, Gian Antonio Susto

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

Matteo Saponati, Pascal Josef Sager, Pau Vilimelis Aceituno, Thilo Stadelmann, Benjamin F Grewe

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

Sunny Sanyal, Hayden Prairie, Rudrajit Das, Ali Kavis, Sujay Sanghavi

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

Pedro Pinto Santos, Alberto Sardinha, Francisco S. Melo

$∞$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation

Saul Santos, António Farinhas, Daniel C Mcnamee, Andre Martins

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

Jeffrey A Chan Santiago, Praveen Tirupattur, Gaurav Kumar Nayak, Gaowen Liu, Mubarak Shah

Collapse-Proof Non-Contrastive Self-Supervised Learning

Emanuele Sansone, Tim Lebailly, Tinne Tuytelaars

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

Suryanarayana Sankagiri, Jalal Etesami, Matthias Grossglauser

Joint Learning of Energy-based Models and their Partition Function

Michael Eli Sander, Vincent Roulet, Tianlin Liu, Mathieu Blondel

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

Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk, Pavel Kolev, Georg Martius

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

David Salinas, Omar Swelam, Frank Hutter

Benign Overfitting in Token Selection of Attention Mechanism

Keitaro Sakamoto, Issei Sato

LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations

Shreshth Saini, Ru-Ling Liao, Yan Ye, Alan Bovik

The Diffusion Duality

Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin T Chiu

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge

Swarnadeep Saha, Xian Li, Marjan Ghazvininejad, Jason E Weston, Tianlu Wang

Dueling Convex Optimization with General Preferences

Aadirupa Saha, Tomer Koren, Yishay Mansour

Adversarial Reasoning at Jailbreaking Time

Mahdi Sabbaghi, Paul Kassianik, George J. Pappas, Amin Karbasi, Hamed Hassani

Disparate Conditional Prediction in Multiclass Classifiers

Sivan Sabato, Eran Treister, Elad Yom-Tov

An Architecture Search Framework for Inference-Time Techniques

Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan, Nahum Maru, Hristo Todorov

A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation

Jongha Jon Ryu, Abhin Shah, Gregory W. Wornell

Value-Based Deep RL Scales Predictably

Oleh Rybkin, Michal Nauman, Preston Fu, Charlie Victor Snell, Pieter Abbeel

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation

Alessio Russo, Aldo Pacchiano

Zero-Shot Offline Imitation Learning via Optimal Transport

Thomas Rupf, Marco Bagatella, Nico Gürtler, Jonas Frey, Georg Martius

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

Anian Ruoss, Fabio Pardo, Harris Chan, Bonnie Li, Volodymyr Mnih

Strategic Planning: A Top-Down Approach to Option Generation

Max Ruiz Luyten, Antonin Berthon, Mihaela van der Schaar

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning

Noa Rubin, Kirsten Fischer, Javed Lindner, Inbar Seroussi, Zohar Ringel

No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions

Benjamin Samuel Ruben, William Lingxiao Tong, Hamza Tahir Chaudhry, Cengiz Pehlevan

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

James Rowbottom, Georg Maierhofer, Teo Deveney, Eike Hermann Müller, Alberto Paganini

Implicit Riemannian Optimism with Applications to Min-Max Problems

Christophe Roux, David Martı́nez-Rubio, Sebastian Pokutta

Loss Functions and Operators Generated by f-Divergences

Vincent Roulet, Tianlin Liu, Nino Vieillard, Michael Eli Sander, Mathieu Blondel

Differential Privacy Under Class Imbalance: Methods and Empirical Insights

Lucas Rosenblatt, Yuliia Lut, Ethan Turok, Marco Avella Medina, Rachel Cummings

Fragments to Facts: Partial-Information Fragment Inference from LLMs

Lucas Rosenblatt, Bin Han, Robert Wolfe, Bill Howe

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

Xuankun Rong, Jianshu Zhang, Kun He, Mang Ye

MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES

Omer Ronen, Ahmed Imtiaz Humayun, Richard Baraniuk, Randall Balestriero, Bin Yu

Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces

Amirhossein Roknilamouki, Arnob Ghosh, Ming Shi, Fatemeh Nourzad, Eylem Ekici

Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

Kevin Rojas, Yuchen Zhu, Sichen Zhu, Felix X-F. Ye, Molei Tao

Towards characterizing the value of edge embeddings in Graph Neural Networks

Dhruv Rohatgi, Tanya Marwah, Zachary Chase Lipton, Jianfeng Lu, Ankur Moitra

Separating Knowledge and Perception with Procedural Data

Adrian Rodriguez-Munoz, Manel Baradad, Phillip Isola, Antonio Torralba

Concept Reachability in Diffusion Models: Beyond Dataset Constraints

Marta Aparicio Rodriguez, Xenia Miscouridou, Anastasia Borovykh

Discrete Neural Algorithmic Reasoning

Gleb Rodionov, Liudmila Prokhorenkova

A Reduction Framework for Distributionally Robust Reinforcement Learning under Average Reward

Zachary Andrew Roch, George K. Atia, Yue Wang

FairPFN: A Tabular Foundation Model for Causal Fairness

Jake Robertson, Noah Hollmann, Samuel Müller, Noor Awad, Frank Hutter

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

Yeonju Ro, Zhenyu Zhang, Souvik Kundu, Zhangyang Wang, Aditya Akella

Resolving Lexical Bias in Model Editing

Hammad Rizwan, Domenic Rosati, Ga Wu, Hassan Sajjad

Progressive Tempering Sampler with Diffusion

Severi Rissanen, Ruikang Ouyang, Jiajun He, Wenlin Chen, Markus Heinonen

Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting

J Rishi, Gvs Mothish, Deepak Subramani

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

Filippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli, Donato Crisostomi, Federico Bolelli

General agents need world models

Jonathan Richens, Tom Everitt, David Abel

Understanding the Logic of Direct Preference Alignment through Logic

Kyle Richardson, Vivek Srikumar, Ashish Sabharwal

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

Fabiola Ricci, Lorenzo Bardone, Sebastian Goldt

Representative Ranking for Deliberation in the Public Sphere

Manon Revel, Smitha Milli, Tyler Lu, Jamelle Watson-Daniels, Maximilian Nickel

Can Transformers Learn Full Bayesian Inference in Context?

Arik Reuter, Tim G. J. Rudner, Vincent Fortuin, David Rügamer

Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation

Roie Reshef, Kfir Yehuda Levy

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

Sucheng Ren, Qihang Yu, Ju He, Xiaohui Shen, Alan Yuille

Inverse Optimization via Learning Feasible Regions

Ke Ren, Peyman Mohajerin Esfahani, Angelos Georghiou

A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization

Kunjie Ren, Luo Luo

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

Zhiyao Ren, Siyuan Liang, Aishan Liu, Dacheng Tao

Multi-View Graph Clustering via Node-Guided Contrastive Encoding

Yazhou Ren, Junlong Ke, Zichen Wen, Tianyi Wu, Yang Yang

Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization

Robbert Reijnen, Yaoxin Wu, Zaharah Bukhsh, Yingqian Zhang

When to retrain a machine learning model

Florence Regol, Leo Schwinn, Kyle Sprague, Mark Coates, Thomas Markovich

RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals

David Reber, Sean M Richardson, Todd Nief, Cristina Gârbacea, Victor Veitch

Towards Memorization Estimation: Fast, Formal and Free

Deepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi, Kaushik Roy

Statistical Hypothesis Testing for Auditing Robustness in Language Models

Paulius Rauba, Qiyao Wei, Mihaela van der Schaar

Adversarial Inception Backdoor Attacks against Reinforcement Learning

Ethan Rathbun, Alina Oprea, Christopher Amato

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings

Saksham Rastogi, Pratyush Maini, Danish Pruthi

Towards Cost-Effective Reward Guided Text Generation

Ahmad Rashid, Ruotian Wu, Rongqi Fan, Hongliang Li, Agustinus Kristiadi

Diffusion Counterfactual Generation with Semantic Abduction

Rajat R Rasal, Avinash Kori, Fabio De Sousa Ribeiro, Tian Xia, Ben Glocker

Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions

Jiahua Rao, Dahao Xu, Wentao Wei, Yicong Chen, Mingjun Yang

FeatSharp: Your Vision Model Features, Sharper

Mike Ranzinger, Greg Heinrich, Pavlo Molchanov, Bryan Catanzaro, Andrew Tao

You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption

Weihang Ran, Wei Yuan, Yinqiang Zheng

Differentially Private Boxplots

Kelly Ramsay, Jairo Diaz-Rodriguez

Communicating Activations Between Language Model Agents

Vignav Ramesh, Kenneth Li

Generation from Noisy Examples

Ananth Raman, Vinod Raman

The Relationship Between No-Regret Learning and Online Conformal Prediction

Ramya Ramalingam, Shayan Kiyani, Aaron Roth

Importance Sampling for Nonlinear Models

Prakash Palanivelu Rajmohan, Fred Roosta

Human-Aligned Image Models Improve Visual Decoding from the Brain

Nona Rajabi, Antônio H. Ribeiro, Miguel Vasco, Farzaneh Taleb, Mårten Björkman

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

Sanjeev Raja, Martin Sipka, Michael Psenka, Tobias Kreiman, Michal Pavelka

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese, Xiao Wang, Adrian Weller

Visual Autoregressive Modeling for Image Super-Resolution

Yunpeng Qu, Kun Yuan, Jinhua Hao, KAI ZHAO, Qizhi Xie

Optimizing Test-Time Compute via Meta Reinforcement Finetuning

Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching