ICLR 2025

3,703 papers

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

Xiangru Zhu, Penglei Sun, Yaoxian Song, Yanghua Xiao, Zhixu Li

A deep inverse-mapping model for a flapping robotic wing

Hadar Sharvit, Raz Karl, Tsevi Beatus

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

Xiaoshuai Song, Muxi Diao, Guanting Dong, Zhengyang Wang, Yujia Fu

From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency

Kaiyue Wen, Huaqing Zhang, Hongzhou Lin, Jingzhao Zhang

FedTMOS: Efficient One-Shot Federated Learning with Tsetlin Machine

Shannon How Shi Qi, Jagmohan Chauhan, Geoff V. Merrett, Jonathon Hare

RMB: Comprehensively benchmarking reward models in LLM alignment

Enyu Zhou, Guodong Zheng, Binghai Wang, Zhiheng Xi, Shihan Dou

What Makes Large Language Models Reason in (Multi-Turn) Code Generation?

Kunhao Zheng, Juliette Decugis, Jonas Gehring, Taco Cohen, Benjamin Negrevergne

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

Sungmin Cha, Sungjun Cho, Dasol Hwang, Moontae Lee

Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions

Michael JQ Zhang, W. Bradley Knox, Eunsol Choi

GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation

Tao Feng, Yihang Sun, Jiaxuan You

Exact Certification of (Graph) Neural Networks Against Label Poisoning

Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann, Debarghya Ghoshdastidar

A Generalist Hanabi Agent

Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond, Miao Liu, Janarthanan Rajendran

Revealing and Mitigating Over-Attention in Knowledge Editing

Pinzheng Wang, Zecheng Tang, Keyan Zhou, Juntao Li, Qiaoming Zhu

GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation

Hongyin Zhang, Pengxiang Ding, Shangke Lyu, Ying Peng, Donglin Wang

Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry

Jannis Chemseddine, Christian Wald, Richard Duong, Gabriele Steidl

Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space

Mohamed Amine Ketata, Nicholas Gao, Johanna Sommer, Tom Wollschläger, Stephan Günnemann

Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization

Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun

Protecting against simultaneous data poisoning attacks

Neel Alex, Shoaib Ahmed Siddiqui, Amartya Sanyal, David Krueger

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

Jaden Fried Fiotto-Kaufman, Alexander Russell Loftus, Eric Todd, Jannik Brinkmann, Koyena Pal

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

Zaid Khan, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal

LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh

Jing Wen, Alex Schwing, Shenlong Wang

High-Dimensional Bayesian Optimisation with Gaussian Process Prior Variational Autoencoders

Siddharth Ramchandran, Manuel Haussmann, Harri Lahdesmaki

RB-Modulation: Training-Free Stylization using Reference-Based Modulation

Litu Rout, Yujia Chen, Nataniel Ruiz, Abhishek Kumar, Constantine Caramanis

From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy

Julian Dörfler, Benito van der Zander, Markus Bläser, Maciej Liśkiewicz

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

Tanqiu Jiang, Zian Wang, Jiacheng Liang, Changjiang Li, Yuhui Wang

Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models

Jianqun Zhou, Yuanlei Zheng, Wei Chen, Qianqian Zheng, Shang Zeyuan

Gaussian Splatting Lucas-Kanade

Liuyue Xie, Joel Julin, Koichiro Niinuma, Laszlo Attila Jeni

Probabilistic Geometric Principal Component Analysis with application to neural data

Han-Lin Hsieh, Maryam Shanechi

KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks

Kaijing Ma, Xeron Du, Yunran Wang, Haoran Zhang, ZhoufutuWen

ContextGNN: Beyond Two-Tower Recommendation Systems

Yiwen Yuan, Zecheng Zhang, Xinwei He, Akihiro Nitta, Weihua Hu

Valid Conformal Prediction for Dynamic GNNs

Ed Davis, Ian Gallagher, Daniel John Lawson, Patrick Rubin-Delanchy

Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs

Bowen Gao, Haichuan Tan, Yanwen Huang, Minsi Ren, Xiao Huang

Inverse decision-making using neural amortized Bayesian actors

Dominik Straub, Tobias F. Niehues, Jan Peters, Constantin A. Rothkopf

Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport

Milena Gazdieva, Jaemoo Choi, Alexander Kolesov, Jaewoong Choi, Petr Mokrov

Revisit the Open Nature of Open Vocabulary Semantic Segmentation

Qiming Huang, Han Hu, Jianbo Jiao

Trajectory-Class-Aware Multi-Agent Reinforcement Learning

Hyungho Na, Kwanghyeon Lee, Sumin Lee, Il-chul Moon

ElasticTok: Adaptive Tokenization for Image and Video

Wilson Yan, Volodymyr Mnih, Aleksandra Faust, Matei Zaharia, Pieter Abbeel

Learning to engineer protein flexibility

Petr Kouba, Joan Planas-Iglesias, Jiri Damborsky, Jiri Sedlar, Stanislav Mazurenko

Quamba: A Post-Training Quantization Recipe for Selective State Space Models

Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Diana Marculescu

World Model on Million-Length Video And Language With Blockwise RingAttention

Hao Liu, Wilson Yan, Matei Zaharia, Pieter Abbeel

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

Jingchu Gai, Yiheng Du, Bohang Zhang, Haggai Maron, Liwei Wang

Fast unsupervised ground metric learning with tree-Wasserstein distance

Kira Michaela Düsterwald, Samo Hromadka, Makoto Yamada

Harnessing Webpage UIs for Text-Rich Visual Understanding

Junpeng Liu, Tianyue Ou, Yifan Song, Yuxiao Qu, Wai Lam

Do Contemporary Causal Inference Models Capture Real-World Heterogeneity? Findings from a Large-Scale Benchmark

Haining Yu, Yizhou Sun

DEPT: Decoupled Embeddings for Pre-training Language Models

Alex Iacob, Lorenzo Sani, Meghdad Kurmanji, William F. Shen, Xinchi Qiu

Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning

Wassim Bouaziz, Nicolas Usunier, El-Mahdi El-Mhamdi

AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies

Jian Gao, Weidong Cao, Junyi Yang, Xuan Zhang

Learning Chaos In A Linear Way

Xiaoyuan Cheng, Yi He, Yiming Yang, Xiao Xue, Sibo Cheng

Provably Safeguarding a Classifier from OOD and Adversarial Samples

Nicolas Atienza, Johanne Cohen, Christophe Labreuche, Michele Sebag

AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution

Fengyuan Liu, Nikhil Kandpal, Colin Raffel

MAESTRO: Masked Encoding Set Transformer with Self-Distillation

Matthew Eric Lee, Jaesik Kim, Matei Ionita, Jonghyun Lee, Michelle L. McKeague

MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science

Erle Zhu, Yadi Liu, Zhe Zhang, Xujun Li, JinZhou

OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data

Shubham Toshniwal, Wei Du, Ivan Moshkov, Branislav Kisačanin, Alexan Ayrapetyan

Consistency Models Made Easy

Zhengyang Geng, Ashwini Pokle, Weijian Luo, Justin Lin, J Zico Kolter

State Space Models are Provably Comparable to Transformers in Dynamic Token Selection

Naoki Nishikawa, Taiji Suzuki

Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

Florian E. Dorner, Vivian Yvonne Nastl, Moritz Hardt

Beyond single neurons: population response geometry in digital twins of mouse visual cortex

Dario Liscai, Emanuele Luconi, Alessandro Marin Vargas, Alessandro Sanzeni

Revisiting Large-Scale Non-convex Distributionally Robust Optimization

Qi Zhang, Yi Zhou, Simon Khan, Ashley Prater-Bennette, Lixin Shen

Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models

Angela Lopez-Cardona, Carlos Segura, Alexandros Karatzoglou, Sergi Abadal, Ioannis Arapakis

Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models

Zeman Li, Xinwei Zhang, Peilin Zhong, Yuan Deng, Meisam Razaviyayn

Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization

Zhitong Xu, Haitao Wang, Jeff M. Phillips, Shandian Zhe

Nesterov acceleration in benignly non-convex landscapes

Kanan Gupta, Stephan Wojtowytsch

Balancing Bias in Two-sided Markets for Fair Stable Matchings

Siyuan Wu, Leong Hou U, Panagiotis Karras

Fugatto 1: Foundational Generative Audio Transformer Opus 1

Rafael Valle, rohan badlani, Zhifeng Kong, Sang-gil Lee, Arushi Goel

Value-aligned Behavior Cloning for Offline Reinforcement Learning via Bi-level Optimization

Xingyu Jiang, Ning Gao, Xiuhui Zhang, Hongkun Dou, Yue Deng

One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment

Christina Sartzetaki, Gemma Roig, Cees G. M. Snoek, Iris Groen

Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs

Severi Rissanen, Markus Heinonen, Arno Solin

Bridging the Data Provenance Gap Across Text, Speech, and Video

Shayne Longpre, Nikhil Singh, Manuel Cherep, Kushagra Tiwary, Joanna Materzynska

Understanding Factual Recall in Transformers via Associative Memories

Eshaan Nichani, Jason D. Lee, Alberto Bietti

The Belief State Transformer

Edward S. Hu, Kwangjun Ahn, Qinghua Liu, Haoran Xu, Manan Tomar

Non-Equilibrium Dynamics of Hybrid Continuous-Discrete Ground-State Sampling

Timothee Leleu, Sam Reifenstein

Diffusion Transformers for Tabular Data Time Series Generation

Fabrizio Garuti, Enver Sangineto, Simone Luetto, Lorenzo Forni, Rita Cucchiara

Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation

Carlos J Soto, Matthew Reimherr, Aleksandra Slavković, Mark Shriver

Interpreting Emergent Planning in Model-Free Reinforcement Learning

Thomas Bush, Stephen Chung, Usman Anwar, Adrià Garriga-Alonso, David Krueger

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

Marcus Williams, Micah Carroll, Adhyyan Narang, Constantin Weisser, Brendan Murphy

Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification

Santiago Cortes-Gomez, Carlos Miguel Patiño, Yewon Byun, Steven Wu, Eric Horvitz

ScImage: How good are multimodal large language models at scientific text-to-image generation?

Leixin Zhang, Steffen Eger, Yinjie Cheng, Weihe Zhai, Jonas Belouadi

Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement Learning

Tian-Shuo Liu, Xu-Hui Liu, Ruifeng Chen, Lixuan Jin, Pengyuan Wang

Generating Freeform Endoskeletal Robots

Muhan Li, Lingji Kong, Sam Kriegman

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models

Bofei Gao, Feifan Song, Zhe Yang, Zefan Cai, yibo miao

Learning Color Equivariant Representations

Yulong Yang, Felix O'Mahony, Christine Allen-Blanchette

Surprising Effectiveness of pretraining Ternary Language Model at Scale

Ayush Kaushal, Tejas Vaidhya, Arnab Kumar Mondal, Tejas Pandey, Aaryan Bhagat

Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic Information

Kyungsu Lee, Haeyun Lee, Jae Youn Hwang

Restructuring Vector Quantization with the Rotation Trick

Christopher Fifty, Ronald Guenther Junkins, Dennis Duan, Aniketh Iyengar, Jerry Weihong Liu

VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration

Dezhan Tu, Danylo Vashchilenko, Yuzhe Lu, Panpan Xu

Mixture of Attentions For Speculative Decoding

Matthieu Zimmer, Milan Gritta, Gerasimos Lampouras, Haitham Bou Ammar, Jun Wang

Causal Graphical Models for Vision-Language Compositional Understanding

Fiorenzo Parascandolo, Nicholas Moratelli, Enver Sangineto, Lorenzo Baraldi, Rita Cucchiara

Active Task Disambiguation with LLMs

Kasia Kobalczyk, Nicolás Astorga, Tennison Liu, Mihaela van der Schaar

SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling

Nikhil Vyas, Depen Morwani, Rosie Zhao, Itai Shapira, David Brandfonbrener

MatExpert: Decomposing Materials Discovery By Mimicking Human Experts

Qianggang Ding, Santiago Miret, Bang Liu

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

Arnav Kumar Jain, Harley Wiltzer, Jesse Farebrother, Irina Rish, Glen Berseth

Quantum (Inspired) D^2-sampling with Applications

Poojan Chetan Shah, Ragesh Jaiswal

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks

Nguyen Hung-Quang, Ngoc-Hieu Nguyen, The-Anh Ta, Thanh Nguyen-Tang, Kok-Seng Wong

ZooProbe: A Data Engine for Evaluating, Exploring, and Evolving Large-scale Training Data for Multimodal LLMs

Yi-Kai Zhang, Shiyin Lu, Qing-Guo Chen, De-Chuan Zhan, Han-Jia Ye

From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle

Kaustubh Vyas, Damien Graux, Yijun Yang, Sebastien Montella, Chenxin Diao

Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent Dimensions

Sagar Shrestha, Xiao Fu

ColPali: Efficient Document Retrieval with Vision Language Models

Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud

Moral Alignment for LLM Agents

Elizaveta Tennant, Stephen Hailes, Mirco Musolesi

KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA

Xiaorui Su, Yibo Wang, Shanghua Gao, Xiaolong Liu, Valentina Giunchiglia

SMT: Fine-Tuning Large Language Models with Sparse Matrices

Haoze He, Juncheng B Li, Xuan Jiang, Heather Miller