ICLR 2025

3,703 papers

Feedback Schrödinger Bridge Matching

Panagiotis Theodoropoulos, Nikolaos Komianos, Vincent Pacelli, Guan-Horng Liu, Evangelos Theodorou

Towards counterfactual fairness through auxiliary variables

Bowei Tian, Ziyao Wang, Shwai He, Wanghao Ye, Guoheng Sun

Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning

Sheng Li, Qitao Tan, Yue Dai, Zhenglun Kong, Tianyu Wang

Learning and aligning single-neuron invariance manifolds in visual cortex

Mohammad Bashiri, Luca Baroni, Ján Antolík, Fabian H. Sinz

MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models

Mohammad Shahab Sepehri, Zalan Fabian, Maryam Soltanolkotabi, Mahdi Soltanolkotabi

TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention

Lijie Yang, Zhihao Zhang, Zhuofu Chen, Zikun Li, Zhihao Jia

Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters

Kevin Li, Sachin Goyal, João D. Semedo, J Zico Kolter

HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR

Hainan Xu, Travis M. Bartley, Vladimir Bataev, Boris Ginsburg

Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations

Yudi Xie, Weichen Huang, Esther Alter, Jeremy Schwartz, Joshua B. Tenenbaum

Can We Talk Models Into Seeing the World Differently?

Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, Muhammad Jehanzeb Mirza

When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers

Hongkang Li, Yihua Zhang, SHUAI ZHANG, Pin-Yu Chen, Sijia Liu

Systems with Switching Causal Relations: A Meta-Causal Perspective

Moritz Willig, Tim Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami

Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits

Zihan Zhang, Xiangyang Ji, Yuan Zhou

ACES: Automatic Cohort Extraction System for Event-Stream Datasets

Justin Xu, Jack Gallifant, Alistair Johnson, Matthew B.A. McDermott

BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments

Xinghao Wang, Pengyu Wang, Bo Wang, Dong Zhang, Yunhua Zhou

Improving Semantic Understanding in Speech Language Models via Brain-tuning

Omer Moussa, Dietrich Klakow, Mariya Toneva

Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification

Hsun-Yu Kuo, Yin-Hsiang Liao, Yu-Chieh Chao, Wei-Yun Ma, Pu-Jen Cheng

Near-Exact Privacy Amplification for Matrix Mechanisms

Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Guha Thakurta

Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting

Suraj Anand, Michael A. Lepori, Jack Merullo, Ellie Pavlick

Concept Bottleneck Large Language Models

Chung-En Sun, Tuomas Oikarinen, Berk Ustun, Tsui-Wei Weng

A Generic Framework for Conformal Fairness

Aditya T. Vadlamani, Anutam Srinivasan, Pranav Maneriker, Ali Payani, Srinivasan Parthasarathy

Towards Foundation Models for Mixed Integer Linear Programming

Sirui Li, Janardhan Kulkarni, Ishai Menache, Cathy Wu, Beibin Li

6D Object Pose Tracking in Internet Videos for Robotic Manipulation

Georgy Ponimatkin, Martin Cífka, Tomáš Souček, Médéric Fourmy, Yann Labbé

FACTS: A Factored State-Space Framework for World Modelling

Li Nanbo, Firas Laakom, Yucheng XU, Wenyi Wang, Jürgen Schmidhuber

Point-based Instance Completion with Scene Constraints

Wesley Khademi, Fuxin Li

Provable unlearning in topic modeling and downstream tasks

Stanley Wei, Sadhika Malladi, Sanjeev Arora, Amartya Sanyal

NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative

Asmar Nadeem, Faegheh Sardari, Robert Dawes, Syed Sameed Husain, Adrian Hilton

Forte : Finding Outliers with Representation Typicality Estimation

Debargha Ganguly, Warren Richard Morningstar, Andrew Seohwan Yu, Vipin Chaudhary

Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks

Zi Wang, Divyam Anshumaan, Ashish Hooda, Yudong Chen, Somesh Jha

Improving Instruction-Following in Language Models through Activation Steering

Alessandro Stolfo, Vidhisha Balachandran, Safoora Yousefi, Eric Horvitz, Besmira Nushi

MuPT: A Generative Symbolic Music Pretrained Transformer

Xingwei Qu, Yuelin Bai, Yinghao Ma, Ziya Zhou, Ka Man Lo

Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling, and Zero-Shot Transfer

Zihan Pengmei, Zhengyuan Shen, Zichen Wang, Marcus D. Collins, Huzefa Rangwala

nGPT: Normalized Transformer with Representation Learning on the Hypersphere

Ilya Loshchilov, Cheng-Ping Hsieh, Simeng Sun, Boris Ginsburg

X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale

Haoran Xu, Kenton Murray, Philipp Koehn, Hieu Hoang, Akiko Eriguchi

Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel

Shivam Gupta, Linda Cai, Sitan Chen

MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse Upcycling

Rachel Teo, Tan Minh Nguyen

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

Tengyang Xie, Dylan J Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Hassan Awadallah

Sufficient Context: A New Lens on Retrieval Augmented Generation Systems

Hailey Joren, Jianyi Zhang, Chun-Sung Ferng, Da-Cheng Juan, Ankur Taly

Preble: Efficient Distributed Prompt Scheduling for LLM Serving

Vikranth Srivatsa, Zijian He, Reyna Abhyankar, Dongming Li, Yiying Zhang

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

Yu Fu, Zefan Cai, Abedelkadir Asi, Wayne Xiong, Yue Dong

Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces

Saket Tiwari, Omer Gottesman, George Konidaris

Certifying Counterfactual Bias in LLMs

Isha Chaudhary, Qian Hu, Manoj Kumar, Morteza Ziyadi, Rahul Gupta

Multilevel Generative Samplers for Investigating Critical Phenomena

Ankur Singha, Elia Cellini, Kim Andrea Nicoli, Karl Jansen, Stefan Kühn

LeanAgent: Lifelong Learning for Formal Theorem Proving

Adarsh Kumarappan, Mo Tiwari, Peiyang Song, Robert Joseph George, Chaowei Xiao

Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions

Peiyao Lai, Oren Mangoubi

Semantic Aware Representation Learning for Lifelong Learning

Fahad Sarfraz, Elahe Arani, Bahram Zonooz

(Mis)Fitting Scaling Laws: A Survey of Scaling Law Fitting Techniques in Deep Learning

Margaret Li, Sneha Kudugunta, Luke Zettlemoyer

Discretization-invariance? On the Discretization Mismatch Errors in Neural Operators

Wenhan Gao, Ruichen Xu, Yuefan Deng, Yi Liu

AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation

Yuning Cui, Syed Waqas Zamir, Salman Khan, Alois Knoll, Mubarak Shah

Robust Feature Learning for Multi-Index Models in High Dimensions

Alireza Mousavi-Hosseini, Adel Javanmard, Murat A Erdogdu

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting

Marcel Kollovieh, Marten Lienen, David Lüdke, Leo Schwinn, Stephan Günnemann

LoLCATs: On Low-Rank Linearizing of Large Language Models

Michael Zhang, Simran Arora, Rahul Chalamala, Benjamin Frederick Spector, Alan Wu

Protein Language Model Fitness is a Matter of Preference

Cade W Gordon, Amy X. Lu, Pieter Abbeel

Self-Play Preference Optimization for Language Model Alignment

Yue Wu, Zhiqing Sun, Huizhuo Yuan, Kaixuan Ji, Yiming Yang

Improving Pretraining Data Using Perplexity Correlations

Tristan Thrush, Christopher Potts, Tatsunori Hashimoto

Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning

Fan Yao, Yuwei Cheng, Ermin Wei, Haifeng Xu

Nonlinear Sequence Embedding by Monotone Variational Inequality

Jonathan Yuyang Zhou, Yao Xie

Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach

Yuchen Liang, Peizhong Ju, Yingbin Liang, Ness Shroff

On the self-verification limitations of large language models on reasoning and planning tasks

Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati

Round and Round We Go! What makes Rotary Positional Encodings useful?

Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu, Petar Veličković

BenTo: Benchmark Reduction with In-Context Transferability

Hongyu Zhao, Ming Li, Lichao Sun, Tianyi Zhou

Law of the Weakest Link: Cross Capabilities of Large Language Models

Ming Zhong, Aston Zhang, Xuewei Wang, Rui Hou, Wenhan Xiong

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

Ziyang Wu, Tianjiao Ding, Yifu Lu, Druv Pai, Jingyuan Zhang

Toward Efficient Multi-Agent Exploration With Trajectory Entropy Maximization

Tianxu Li, Kun Zhu

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

Javier Ferrando, Oscar Balcells Obeso, Senthooran Rajamanoharan, Neel Nanda

Provable weak-to-strong generalization via benign overfitting

David Xing Wu, Anant Sahai

HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics

Jingxuan Fan, Sarah Martinson, Erik Y. Wang, Kaylie Hausknecht, Jonah Brenner

STAR: Synthesis of Tailored Architectures

Armin W Thomas, Rom Parnichkun, Alexander Amini, Stefano Massaroli, Michael Poli

Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games

Yang Cai, Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

Mude Hui, Siwei Yang, Bingchen Zhao, Yichun Shi, Heng Wang

MCNC: Manifold-Constrained Reparameterization for Neural Compression

Chayne Thrash, Reed Andreas, Ali Abbasi, Parsa Nooralinejad, Soroush Abbasi Koohpayegani

Residual-MPPI: Online Policy Customization for Continuous Control

Pengcheng Wang, Chenran Li, Catherine Weaver, Kenta Kawamoto, Masayoshi Tomizuka

Machine Unlearning Fails to Remove Data Poisoning Attacks

Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu, Gautam Kamath, Ayush Sekhari

RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank

Tanya Chowdhury, Yair Zick, James Allan

Misspecified Q-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error

Ally Yalei Du, Lin Yang, Ruosong Wang

Steering Large Language Models between Code Execution and Textual Reasoning

Yongchao Chen, Harsh Jhamtani, Srinagesh Sharma, Chuchu Fan, Chi Wang

Can Large Language Models Understand Symbolic Graphics Programs?

Zeju Qiu, Weiyang Liu, Haiwen Feng, Zhen Liu, Tim Z. Xiao

Beyond Worst-Case Dimensionality Reduction for Sparse Vectors

Sandeep Silwal, David Woodruff, Qiuyi Zhang

First-Person Fairness in Chatbots

Tyna Eloundou, Alex Beutel, David G. Robinson, Keren Gu, Anna-Luisa Brakman

Tamper-Resistant Safeguards for Open-Weight LLMs

Rishub Tamirisa, Bhrugu Bharathi, Long Phan, Andy Zhou, Alice Gatti

E(n) Equivariant Topological Neural Networks

Claudio Battiloro, Ege Karaismailoglu, Mauricio Tec, George Dasoulas, Michelle Audirac

eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels

Alexander DeRieux, Walid Saad

Robust System Identification: Finite-sample Guarantees and Connection to Regularization

Hyuk Park, Grani A. Hanasusanto, Yingying Li

Reconciling Model Multiplicity for Downstream Decision Making

Ally Yalei Du, Dung Daniel Ngo, Steven Wu

Transformer Block Coupling and its Correlation with Generalization in LLMs

Murdock Aubry, Haoming Meng, Anton Sugolov, Vardan Papyan

Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits

Ashish J Khisti, MohammadReza Ebrahimi, Hassan Dbouk, Arash Behboodi, Roland Memisevic

CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution

Yunju Cho, Jay-Yoon Lee

SPDIM: Source-Free Unsupervised Conditional and Label Shift Adaptation in EEG

Shanglin Li, Motoaki Kawanabe, Reinmar J Kobler

IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning

Vindula Jayawardana, Baptiste Freydt, Ao Qu, Cameron Hickert, Zhongxia Yan

Lightweight Predictive 3D Gaussian Splats

Junli Cao, Vidit Goel, Chaoyang Wang, Anil Kag, Ju Hu

Intermediate Layer Classifiers for OOD generalization

Arnas Uselis, Seong Joon Oh

Towards Bridging Generalization and Expressivity of Graph Neural Networks

Shouheng Li, Floris Geerts, Dongwoo Kim, Qing Wang

VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning

Yichao Liang, Nishanth Kumar, Hao Tang, Adrian Weller, Joshua B. Tenenbaum

Enhancing Learning with Label Differential Privacy by Vector Approximation

Puning Zhao, Jiafei Wu, Zhe Liu, Li Shen, Zhikun Zhang

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

Fengyu Gao, Ruida Zhou, Tianhao Wang, Cong Shen, Jing Yang

How to Find the Exact Pareto Front for Multi-Objective MDPs?

Yining Li, Peizhong Ju, Ness Shroff

Neural Spacetimes for DAG Representation Learning

Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong, Michael M. Bronstein

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

Yinlam Chow, Guy Tennenholtz, Izzeddin Gur, Vincent Zhuang, Bo Dai

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan

Variational Search Distributions

Daniel M. Steinberg, Rafael Oliveira, Cheng Soon Ong, Edwin V. Bonilla