ICLR 2025

3,703 papers

Strong Model Collapse

Elvis DOHMATOB, Yunzhen Feng, Arjun Subramonian, Julia Kempe

Systematic Outliers in Large Language Models

Yongqi An, Xu Zhao, Tao Yu, Ming Tang, Jinqiao Wang

Shh, don't say that! Domain Certification in LLMs

Cornelius Emde, Alasdair Paren, Preetham Arvind, Maxime Guillaume Kayser, Tom Rainforth

Mask in the Mirror: Implicit Sparsification

Tom Jacobs, Rebekka Burkholz

Learning to Communicate Through Implicit Communication Channels

Han Wang, Binbin Chen, Tieying Zhang, Baoxiang Wang

UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP

Wenzheng Pan, Hao Xiong, Jiale Ma, Wentao Zhao, Yang Li

Streamlining Prediction in Bayesian Deep Learning

Rui Li, Marcus Klasson, Arno Solin, Martin Trapp

PersonalLLM: Tailoring LLMs to Individual Preferences

Thomas P Zollo, Andrew Wei Tung Siah, Naimeng Ye, Ang Li, Hongseok Namkoong

Adversarial Training for Defense Against Label Poisoning Attacks

Melis Ilayda Bal, Volkan Cevher, Michael Muehlebach

3DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation

Dewei Zhou, Ji Xie, Zongxin Yang, Yi Yang

AtomSurf: Surface Representation for Learning on Protein Structures

Vincent Mallet, Yangyang Miao, Souhaib Attaiki, Bruno Correia, Maks Ovsjanikov

ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance

Jiannan Huang, Jun Hao Liew, Hanshu Yan, Yuyang Yin, Yao Zhao

Solving Differential Equations with Constrained Learning

Viggo Moro, Luiz F. O. Chamon

Dynamic Negative Guidance of Diffusion Models

Felix Koulischer, Johannes Deleu, Gabriel Raya, Thomas Demeester, Luca Ambrogioni

Boosting Latent Diffusion with Perceptual Objectives

Tariq Berrada, Pietro Astolfi, Melissa Hall, Marton Havasi, Yohann Benchetrit

On the Crucial Role of Initialization for Matrix Factorization

Bingcong Li, Liang Zhang, Aryan Mokhtari, Niao He

Improved Training Technique for Latent Consistency Models

Quan Dao, Khanh Doan, Di Liu, Trung Le, Dimitris N. Metaxas

Encryption-Friendly LLM Architecture

Donghwan Rho, Taeseong Kim, Minje Park, Jung woo Kim, Hyunsik Chae

Leave-One-Out Stable Conformal Prediction

Kiljae Lee, yuan zhang

A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning

Chen-Yu Liu, Chao-Han Huck Yang, Hsi-Sheng Goan, Min-Hsiu Hsieh

Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy

Ishank Juneja, Carlee Joe-Wong, Osman Yagan

Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors

Chen Ma, Xinjie Xu, Shuyu Cheng, Qi Xuan

Revisiting a Design Choice in Gradient Temporal Difference Learning

Xiaochi Qian, Shangtong Zhang

Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

Zhaowei Zhang, Fengshuo Bai, Qizhi Chen, Chengdong Ma, Mingzhi Wang

Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint

Guangkun Nie, Gongzheng Tang, Shenda Hong

Grammar Reinforcement Learning: path and cycle counting in graphs with a Context-Free Grammar and Transformer approach

Jason Piquenot, Maxime Berar, Romain Raveaux, Pierre Héroux, Jean-Yves RAMEL

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures

Junxuan Wang, Xuyang Ge, Wentao Shu, Qiong Tang, Yunhua Zhou

BOND: Aligning LLMs with Best-of-N Distillation

Pier Giuseppe Sessa, Robert Dadashi-Tazehozi, Leonard Hussenot, Johan Ferret, Nino Vieillard

Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness

Maayan Ehrenberg, Roy Ganz, Nir Rosenfeld

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Yam Eitan, Yoav Gelberg, Guy Bar-Shalom, Fabrizio Frasca, Michael M. Bronstein

Select before Act: Spatially Decoupled Action Repetition for Continuous Control

Buqing Nie, Yangqing Fu, Yue Gao

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models

Nguyen Hoang Khoi Do, Truc Nguyen, Malik Hassanaly, raed alharbi, Jung Taek Seo

CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching

Xingjian Wu, Xiangfei Qiu, Zhengyu Li, Yihang Wang, Jilin Hu

Improved Sampling Of Diffusion Models In Fluid Dynamics With Tweedie's Formula

Youssef Shehata, Benjamin Holzschuh, Nils Thuerey

REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring

Taewon Kim, Hyunjin Seo, Sungsoo Ahn, Eunho Yang

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs

Jonas Hübotter, Sascha Bongni, Ido Hakimi, Andreas Krause

KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI

Jaron Maene, Vincent Derkinderen, Pedro Zuidberg Dos Martires

Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment

Yankai Jiang, Wenhui Lei, Xiaofan Zhang, Shaoting Zhang

Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data

Binghui Li, Yuanzhi Li

Text2PDE: Latent Diffusion Models for Accessible Physics Simulation

Anthony Zhou, Zijie Li, Michael Schneier, John R Buchanan Jr, Amir Barati Farimani

A New Perspective on Shampoo's Preconditioner

Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham M. Kakade

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

Jiarui Jin, Haoyu Wang, Hongyan Li, Jun Li, Jiahui Pan

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

Junjie Li, Yang Liu, Weiqing Liu, Shikai Fang, Lewen Wang

Deep Random Features for Scalable Interpolation of Spatiotemporal Data

Weibin Chen, Azhir Mahmood, Michel Tsamados, So Takao

Explanations of GNN on Evolving Graphs via Axiomatic Layer edges

Yazheng Liu, Sihong Xie

Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold

Sixin Zhang

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

Bowen Jin, Jinsung Yoon, Jiawei Han, Sercan O Arik

I-Con: A Unifying Framework for Representation Learning

Shaden Naif Alshammari, John R. Hershey, Axel Feldmann, William T. Freeman, Mark Hamilton

Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

Levi Rauchwerger, Stefanie Jegelka, Ron Levie

RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement Learning

Qianlan Yang, Yu-Xiong Wang

SWEb: A Large Web Dataset for the Scandinavian Languages

Tobias Norlund, Tim Isbister, Amaru Cuba Gyllensten, Paul Gabriel dos Santos, Danila Petrelli

Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports

Yi Xu, Yun Fu

Binary Losses for Density Ratio Estimation

Werner Zellinger

Accessing Vision Foundation Models via ImageNet-1K

Yitian Zhang, Xu Ma, Yue Bai, Huan Wang, Yun Fu

CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design

Wenji Fang, Shang Liu, Jing Wang, Zhiyao Xie

Input Space Mode Connectivity in Deep Neural Networks

Jakub Vrabel, Ori Shem-Ur, Yaron Oz, David Krueger

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Changgan Yin

Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint

Jiafei Lyu, Mengbei Yan, Zhongjian Qiao, Runze Liu, Xiaoteng Ma

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

Marco Mistretta, Alberto Baldrati, Lorenzo Agnolucci, Marco Bertini, Andrew D. Bagdanov

Fast Uncovering of Protein Sequence Diversity from Structure

luca alessandro silva, Barthelemy Meynard-Piganeau, Carlo Lucibello, Christoph Feinauer

Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation

Tobias Leemann, Periklis Petridis, Giuseppe Vietri, Dionysis Manousakas, Aaron Roth

Learning to Solve Differential Equation Constrained Optimization Problems

Vincenzo Di Vito Francesco, Mostafa Mohammadian, Kyri Baker, Ferdinando Fioretto

Optimizing importance weighting in the presence of sub-population shifts

Floris Holstege, Bram Wouters, Noud Van Giersbergen, Cees Diks

Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

Tai Hoang, Huy Le, Philipp Becker, Vien Anh Ngo, Gerhard Neumann

GOAL: A Generalist Combinatorial Optimization Agent Learner

Darko Drakulic, Sofia Michel, Jean-Marc Andreoli

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks

Binghui Li, Zhixuan Pan, Kaifeng Lyu, Jian Li

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception

Rui Zhang, Ruixu Geng, Yadong Li, Ruiyuan Song, Hanqin Gong

Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection

Hongru Yan, Yu Zheng, Yueqi Duan

Preference Elicitation for Offline Reinforcement Learning

Alizée Pace, Bernhard Schölkopf, Gunnar Rätsch, Giorgia Ramponi

TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting

Songtao Huang, Zhen Zhao, Can Li, LEI BAI

Bayesian Image Regression with Soft-thresholded Conditional Autoregressive Prior

Yuliang Xu, Jian Kang

InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping

Yunchao Zhang, Guandao Yang, Leonidas Guibas, Yanchao Yang

Continuous Exposure Learning for Low-light Image Enhancement using Neural ODEs

Donggoo Jung, Daehyun Kim, Tae Hyun Kim

Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering

Yibo Zhang, Lihong Wang, Changqing Zou, Tieru Wu, Rui Ma

ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension

Tianren Ma, Lingxi Xie, Yunjie Tian, Boyu Yang, Qixiang Ye

Towards Marginal Fairness Sliced Wasserstein Barycenter

Khai Nguyen, Hai Nguyen, nhật Hồ

Interpreting the Second-Order Effects of Neurons in CLIP

Yossi Gandelsman, Alexei A Efros, Jacob Steinhardt

Multi-Label Node Classification with Label Influence Propagation

Yifei Sun, Zemin Liu, Bryan Hooi, Yang Yang, Rizal Fathony

Implicit Neural Surface Deformation with Explicit Velocity Fields

Lu Sang, Zehranaz Canfes, Dongliang Cao, Florian Bernard, Daniel Cremers

High-quality Text-to-3D Character Generation with SparseCubes and Sparse Transformers.

Jiachen Qian, Hongye Yang, Shuang Wu, Jingxi Xu, FEIHU ZHANG

DiffPuter: Empowering Diffusion Models for Missing Data Imputation

Hengrui Zhang, Liancheng Fang, Qitian Wu, Philip S. Yu

Zero-shot Model-based Reinforcement Learning using Large Language Models

Abdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat, Oussama Zekri, Albert Thomas

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation

Itamar Zimerman, Ameen Ali Ali, Lior Wolf

Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos

Gengshan Yang, Andrea Bajcsy, Shunsuke Saito, Angjoo Kanazawa

A Periodic Bayesian Flow for Material Generation

Hanlin Wu, Yuxuan Song, Jingjing Gong, Ziyao Cao, Yawen Ouyang

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

Yongxin Guo, Zhenglin Cheng, Xiaoying Tang, Zhaopeng Tu, Tao LIN

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness

Aaron Jiaxun Li, Satyapriya Krishna, Himabindu Lakkaraju

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Xiaojun Jia, Tianyu Pang, Chao Du, Yihao Huang, Jindong Gu

A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence

Mingyang Liu, Gabriele Farina, Asuman E. Ozdaglar

Towards Certification of Uncertainty Calibration under Adversarial Attacks

Cornelius Emde, Francesco Pinto, Thomas Lukasiewicz, Philip Torr, Adel Bibi

Measuring memorization in RLHF for code completion

Jamie Hayes, Ilia Shumailov, William P. Porter, Aneesh Pappu

Range, not Independence, Drives Modularity in Biologically Inspired Representations

Will Dorrell, Kyle Hsu, Luke Hollingsworth, Jin Hwa Lee, Jiajun Wu

AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning

Yuanfei Wang, Xiaojie Zhang, Ruihai Wu, Yu Li, Yan Shen

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

peng gao, Le Zhuo, Dongyang Liu, Ruoyi Du, Xu Luo

ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafish

Jan-Matthis Lueckmann, Alexander Immer, Alex Bo-Yuan Chen, Peter H. Li, Mariela D Petkova

Do LLMs have Consistent Values?

Naama Rozen, Liat Bezalel, Gal Elidan, Amir Globerson, Ella Daniel

Contextual Document Embeddings

John Xavier Morris, Alexander M Rush

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

Tianci Liu, Ruirui Li, Yunzhe Qi, Hui LIU, Xianfeng Tang

Multi-modal brain encoding models for multi-modal stimuli

Subba Reddy Oota, Khushbu Pahwa, Mounika Marreddy, Maneesh Kumar Singh, Manish Gupta