ICLR 2025

3,703 papers

Risk-Sensitive Variational Actor-Critic: A Model-Based Approach

Alonso Granados, Reza Ebrahimi, Jason Pacheco

ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization

Chen Bo Calvin Zhang, Zhang-Wei Hong, Aldo Pacchiano, Pulkit Agrawal

No Need to Talk: Asynchronous Mixture of Language Models

Anastasiia Filippova, Angelos Katharopoulos, David Grangier, Ronan Collobert

Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration

Heyang Zhao, Xingrui Yu, David Mark Bossens, Ivor Tsang, Quanquan Gu

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

Shicong Cen, Jincheng Mei, Katayoon Goshvadi, Hanjun Dai, Tong Yang

AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

Ke Yang, Yao Liu, Sapana Chaudhary, Rasool Fakoor, Pratik Chaudhari

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov, Mikael Henaff, Roberta Raileanu, Shagun Sodhani, Pascal Vincent

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing

Qi Le, Enmao Diao, Ziyan Wang, Xinran Wang, Jie Ding

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors

Tianchun Wang, Yuanzhou Chen, Zichuan Liu, Zhanwen Chen, Haifeng Chen

Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling

Sirui Li, Wenbin Ouyang, Yining Ma, Cathy Wu

ImProver: Agent-Based Automated Proof Optimization

Riyaz Ahuja, Jeremy Avigad, Prasad Tetali, Sean Welleck

Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models

Jung Hyun Lee, June Yong Yang, Byeongho Heo, Dongyoon Han, Kyungsu Kim

Reward Learning from Multiple Feedback Types

Yannick Metz, Andras Geiszl, Raphaël Baur, Mennatallah El-Assady

Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

Chengyue Huang, Junjiao Tian, Brisa Maneechotesuwan, Shivang Chopra, Zsolt Kira

When narrower is better: the narrow width limit of Bayesian parallel branching neural networks

Zechen Zhang, Haim Sompolinsky

Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration

Chen Jiang, Jiahui An, Yating Liu, Ni Ji

Discovering Influential Neuron Path in Vision Transformers

Yifan Wang, Yifei Liu, Yingdong Shi, Changming Li, Anqi Pang

Learning-Augmented Frequent Directions

Anders Aamand, Justin Y. Chen, Siddharth Gollapudi, Sandeep Silwal, Hao Wu

Can Watermarks be Used to Detect LLM IP Infringement For Free?

Zhengyue Zhao, Xiaogeng Liu, Somesh Jha, Patrick McDaniel, Bo Li

More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed Routing

Sagi Shaier, Francisco Pereira, Katharina von der Wense, Lawrence Hunter, Matt Jones

In-context Time Series Predictor

Jiecheng Lu, Yan Sun, Shihao Yang

Uncertainty Herding: One Active Learning Method for All Label Budgets

Wonho Bae, Danica J. Sutherland, Gabriel L. Oliveira

Efficient Biological Data Acquisition through Inference Set Design

Ihor Neporozhnii, Julien Roy, Emmanuel Bengio, Jason Hartford

Specialized Foundation Models Struggle to Beat Supervised Baselines

Zongzhe Xu, Ritvik Gupta, Wenduo Cheng, Alexander Shen, Junhong Shen

Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning

Zijian Guo, Weichao Zhou, Shengao Wang, Wenchao Li

Conformal Language Model Reasoning with Coherent Factuality

Maxon Rubin-Toles, Maya Gambhir, Keshav Ramji, Aaron Roth, Surbhi Goel

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains

wonje choi, Jinwoo Park, Sanghyun Ahn, Daehee Lee, Honguk Woo

Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention

Tongzhou Liao, Barnabás Póczos

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu

Dissecting Adversarial Robustness of Multimodal LM Agents

Chen Henry Wu, Rishi Rajesh Shah, Jing Yu Koh, Russ Salakhutdinov, Daniel Fried

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

Rasoul Shafipour, David Harrison, Maxwell Horton, JEFFREY MARKER, Houman Bedayat

CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic Screening

Gen Zhou, Sugitha Janarthanan, Yutong Lu, Pingzhao Hu

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Aleksandar Makelov, Georg Lange, Neel Nanda

Commit0: Library Generation from Scratch

Wenting Zhao, Nan Jiang, Celine Lee, Justin T Chiu, Claire Cardie

VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems

Xudong Gong, Feng Dawei, Kele Xu, Weijia Wang, Zhangjun Sun

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

Julie Kallini, Shikhar Murty, Christopher D Manning, Christopher Potts, Róbert Csordás

Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Mufei Li, Siqi Miao, Pan Li

RazorAttention: Efficient KV Cache Compression Through Retrieval Heads

Hanlin Tang, Yang Lin, Jing Lin, Qingsen Han, Danning Ke

ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang

Efficient Top-m Data Values Identification for Data Selection

Xiaoqiang Lin, Xinyi Xu, See-Kiong Ng, Bryan Kian Hsiang Low

Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL Assortment

Aadirupa Saha, Pierre Gaillard

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment

Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag, Soumya Suvra Ghosal, Jiahao Qiu

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

Yu Ying Chiu, Liwei Jiang, Yejin Choi

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Zhenting Qi, Hanlin Zhang, Eric P. Xing, Sham M. Kakade, Himabindu Lakkaraju

SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?

John Yang, Carlos E Jimenez, Alex L Zhang, Kilian Lieret, Joyce Yang

PEARL: Towards Permutation-Resilient LLMs

Liang Chen, Li Shen, Yang Deng, Xiaoyan Zhao, Bin Liang

What's the Move? Hybrid Imitation Learning via Salient Points

Priya Sundaresan, Hengyuan Hu, Quan Vuong, Jeannette Bohg, Dorsa Sadigh

LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases

Armin Toroghi, Ali Pesaranghader, Tanmana Sadhu, Scott Sanner

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

Mufei Li, Viraj Shitole, Eli Chien, Changhai Man, Zhaodong Wang

BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral Data

Parsa Vahidi, Omid G. Sani, Maryam Shanechi

Robustness Reprogramming for Representation Learning

Zhichao Hou, MohamadAli Torkamani, Hamid Krim, Xiaorui Liu

Forking Paths in Neural Text Generation

Eric J Bigelow, Ari Holtzman, Hidenori Tanaka, Tomer Ullman

Counterfactual Realizability

Arvind Raghavan, Elias Bareinboim

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment

Dongyoung Kim, Kimin Lee, Jinwoo Shin, Jaehyung Kim

LICO: Large Language Models for In-Context Molecular Optimization

Tung Nguyen, Aditya Grover

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

Doohyuk Jang, Sihwan Park, June Yong Yang, Yeonsung Jung, Jihun Yun

Efficient Causal Decision Making with One-sided Feedback

Jianing Chu, Shu Yang, Wenbin Lu, PULAK GHOSH

GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

Sarkar Snigdha Sarathi Das, Ryo Kamoi, Bo Pang, Yusen Zhang, Caiming Xiong

Prompting Fairness: Integrating Causality to Debias Large Language Models

Jingling Li, Zeyu Tang, Xiaoyu Liu, Peter Spirtes, Kun Zhang

LocoVR: Multiuser Indoor Locomotion Dataset in Virtual Reality

Kojiro Takeyama, Yimeng Liu, Misha Sra

EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

Kaizhi Zheng, Xiaotong Chen, Xuehai He, Jing Gu, Linjie Li

DataMan: Data Manager for Pre-training Large Language Models

Ru Peng, Kexin Yang, Yawen Zeng, Junyang Lin, Dayiheng Liu

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

Jonathan Light, Min Cai, Weiqin Chen, Guanzhi Wang, Xiusi Chen

LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid

Tianyi Zhang, Anshumali Shrivastava

Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment

Chenliang Li, Siliang Zeng, Zeyi Liao, Jiaxiang Li, Dongyeop Kang

Modeling Complex System Dynamics with Flow Matching Across Time and Conditions

Martin Rohbeck, Edward De Brouwer, Charlotte Bunne, Jan-Christian Huetter, Anne Biton

ProteinBench: A Holistic Evaluation of Protein Foundation Models

Fei Ye, Zaixiang Zheng, Dongyu Xue, Yuning Shen, Lihao Wang

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

Yu Huang, Zixin Wen, Yuejie Chi, Yingbin Liang

Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception

Zihan Ding, Jiahui Fu, Si Liu, Hongyu Li, Siheng Chen

Image Watermarks are Removable using Controllable Regeneration from Clean Noise

Yepeng Liu, Yiren Song, Hai Ci, Yu Zhang, Haofan Wang

Discovering Group Structures via Unitary Representation Learning

Dongsung Huh

Identifiability for Gaussian Processes with Holomorphic Kernels

Ameer Qaqish, Didong Li

SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation

Jongmin Lee, Meiqi Sun, Pieter Abbeel

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Seyed Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks

Jiuding Sun, Jing Huang, Sidharth Baskaran, Karel D'Oosterlinck, Christopher Potts

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Ziteng Wang, Jun Zhu, Jianfei Chen

Consistency Checks for Language Model Forecasters

Daniel Paleka, Abhimanyu Pallavi Sudhir, Alejandro Alvarez, Vineeth Bhat, Adam Shen

Score-based Self-supervised MRI Denoising

Jiachen Tu, Yaokun Shi, Fan Lam

RouteLLM: Learning to Route LLMs from Preference Data

Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

Siyu Chen, Beining Wu, Miao Lu, Zhuoran Yang, Tianhao Wang

Toward Understanding In-context vs. In-weight Learning

Bryan Chan, Xinyi Chen, András György, Dale Schuurmans

LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace

yan yang, Bin Gao, Ya-xiang Yuan

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza

Forgetting Transformer: Softmax Attention with a Forget Gate

Zhixuan Lin, Evgenii Nikishin, Xu He, Aaron Courville

Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees

Gautam Chandrasekaran, Adam Klivans, Lin Lin Lee, Konstantinos Stavropoulos

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

Xingchen Wan, Han Zhou, Ruoxi Sun, Sercan O Arik

On Stochastic Contextual Bandits with Knapsacks in Small Budget Regime

Hengquan Guo, Xin Liu

PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS

Yilong Li, Jingyu Liu, Hao Zhang, M Badri Narayanan, Utkarsh Sharma

A Formal Framework for Understanding Length Generalization in Transformers

Xinting Huang, Andy Yang, Satwik Bhattamishra, Yash Sarrof, Andreas Krebs

Generating CAD Code with Vision-Language Models for 3D Designs

Kamel Alrashedy, Pradyumna Tambwekar, Zulfiqar Haider Zaidi, Megan Langwasser, Wei Xu

Mastering Task Arithmetic: τJp as a Key Indicator for Weight Disentanglement

Kotaro Yoshida, Yuji Naraki, Takafumi Horie, Ryosuke Yamaki, Ryotaro Shimizu

AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption

Joonsung Jeon, Woo Jae Kim, Suhyeon Ha, Sooel Son, Sung-eui Yoon

Scalable Influence and Fact Tracing for Large Language Model Pretraining

Tyler A. Chang, Dheeraj Rajagopal, Tolga Bolukbasi, Lucas Dixon, Ian Tenney

Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection

Chunlei Li, Yilei Shi, Jingliang Hu, Xiao Xiang Zhu, Lichao Mou

Learning Efficient Positional Encodings with Graph Neural Networks

Charilaos Kanatsoulis, Evelyn Choi, Stefanie Jegelka, Jure Leskovec, Alejandro Ribeiro

Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction

Baiting Luo, Ava Pettet, Aron Laszka, Abhishek Dubey, Ayan Mukhopadhyay

Towards Learning High-Precision Least Squares Algorithms with Sequence Models

Jerry Weihong Liu, Jessica Grogan, Owen M Dugan, Ashish Rao, Simran Arora

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct

Christopher Ackerman, Nina Panickssery

Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers

Shijie Chen, Bernal Jiménez Gutiérrez, Yu Su

TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models

Ziyao Shangguan, Chuhan Li, Yuxuan Ding, Yanan Zheng, Yilun Zhao