ICLR 2025

3,703 papers

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

Yuxin Jiang, Bo Huang, Yufei Wang, Xingshan Zeng, Liangyou Li

Erasing Concept Combination from Text-to-Image Diffusion Model

hongyi nie, Quanming Yao, Yang Liu, Zhen Wang, Yatao Bian

DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation

Xinghao Chen, Siwei Li, Yijing Yang, Yunhe Wang

MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn

SysBench: Can LLMs Follow System Message?

Yanzhao Qin, Tao Zhang, Yanjun Shen, Wenjing Luo, sunhaoze

Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers

Quoc-Vinh Lai-Dang, Taemin Kang, Seungah Son

Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation

Kim Yong Tan, Yueming LYU, Ivor Tsang, Yew-Soon Ong

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li

SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting

Huajian Huang, Yingshu Chen, Longwei Li, Hui Cheng, Tristan Braud

Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs

Steve Azzolin, Antonio Longa, Stefano Teso, Andrea Passerini

Bootstrapping Language Models with DPO Implicit Rewards

Changyu CHEN, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu

Learning system dynamics without forgetting

Xikun Zhang, Dongjin Song, Yushan Jiang, Yixin Chen, Dacheng Tao

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran

Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating

Olivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kajić, Su Wang

Model Risk-sensitive Offline Reinforcement Learning

Gwangpyo Yoo, Honguk Woo

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

Kepan Nan, Rui Xie, Penghao Zhou, Tiehan Fan, Zhenheng Yang

Standardizing Structural Causal Models

Weronika Ormaniec, Scott Sussex, Lars Lorch, Bernhard Schölkopf, Andreas Krause

Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model

Yaxuan Huang, xili dai, Jianan Wang, Xianbiao Qi, Yixing Yuan

Learning Hierarchical Polynomials of Multiple Nonlinear Features

Hengyu Fu, Zihao Wang, Eshaan Nichani, Jason D. Lee

ELBOing Stein: Variational Bayes with Stein Mixture Inference

Ola Rønning, Eric Nalisnick, Christophe Ley, Padhraic Smyth, Thomas Hamelryck

Training-free LLM-generated Text Detection by Mining Token Probability Sequences

Yihuai Xu, Yongwei Wang, Yifei Bi, Huangsen Cao, Zhouhan Lin

Fast training and sampling of Restricted Boltzmann Machines

Nicolas BEREUX, Aurélien Decelle, Cyril Furtlehner, Lorenzo Rosset, Beatriz Seoane

Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data

Hengyu Fu, Zehao Dou, Jiawei Guo, Mengdi Wang, Minshuo Chen

Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning

Marco Sälzer, Eric Alsmann, Martin Lange

Dataset Ownership Verification in Contrastive Pre-trained Models

Yuechen Xie, Jie Song, Mengqi Xue, Haofei Zhang, Xingen Wang

AI Sandbagging: Language Models can Strategically Underperform on Evaluations

Teun van der Weij, Felix Hofstätter, Oliver Jaffe, Samuel F. Brown, Francis Rhys Ward

Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization

Rei Higuchi, Pierre-Louis Poirion, Akiko Takeda

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models

Yan Scholten, Stephan Günnemann, Leo Schwinn

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

Justin Deschenaux, Caglar Gulcehre

DoF: A Diffusion Factorization Framework for Offline Multi-Agent Reinforcement Learning

CHAO LI, Ziwei Deng, Chenxing Lin, Wenqi Chen, Yongquan Fu

Subgraph Federated Learning for Local Generalization

Sungwon Kim, Yoonho Lee, Yunhak Oh, Namkyeong Lee, Sukwon Yun

MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

Xuannan Liu, Zekun Li, Pei Pei Li, Huaibo Huang, Shuhan Xia

COPER: Correlation-based Permutations for Multi-View Clustering

Ran Eisenberg, Jonathan Svirsky, Ofir Lindenbaum

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang, Andy T. Liu, Chen-An Li

Regularizing Energy among Training Samples for Out-of-Distribution Generalization

Yiting Chen, Qitian Wu, Junchi Yan

On the Relation between Trainability and Dequantization of Variational Quantum Learning Models

Elies Gil-Fuster, Casper Gyurik, Adrian Perez-Salinas, Vedran Dunjko

DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector

Jinghan Li, Yuan Gao, Jinda Lu, Junfeng Fang, Congcong Wen

MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba

Masakazu Yoshimura, Teruaki Hayashi, Yota Maeda

SparsyFed: Sparse Adaptive Federated Learning

Adriano Guastella, Lorenzo Sani, Alex Iacob, Alessio Mora, Paolo Bellavista

A Tight Convergence Analysis of Inexact Stochastic Proximal Point Algorithm for Stochastic Composite Optimization Problems

Shulan Zhu, Chenglong Bao, Defeng Sun, Yancheng Yuan

Mitigate the Gap: Improving Cross-Modal Alignment in CLIP

Sedigheh Eslami, Gerard de Melo

Tell me about yourself: LLMs are aware of their learned behaviors

Jan Betley, Xuchan Bao, Martín Soto, Anna Sztyber-Betley, James Chua

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian

The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions

Stefan Sylvius Wagner, Maike Behrendt, Marc Ziegele, Stefan Harmeling

Intrinsic User-Centric Interpretability through Global Mixture of Experts

Vinitra Swamy, Syrielle Montariol, Julian Blackwell, Jibril Frej, Martin Jaggi

Multi-Perspective Data Augmentation for Few-shot Object Detection

Anh Khoa Nguyen Vu, Truong Quoc Truong, Vinh-Tiep Nguyen, Thanh Duc Ngo, Thanh-Toan Do

EVA: Geometric Inverse Design for Fast Protein Motif-Scaffolding with Coupled Flow

Yufei Huang, Yunshu Liu, Lirong Wu, Haitao Lin, Cheng Tan

AgentStudio: A Toolkit for Building General Virtual Agents

Longtao Zheng, Zhiyuan Huang, Zhenghai Xue, Xinrun Wang, Bo An

econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians

Can Zhang, Gim Hee Lee

Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

Jiasheng Ye, Peiju Liu, Tianxiang Sun, Jun Zhan, Yunhua Zhou

Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation

Rong Tang, Lizhen Lin, Yun Yang

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

Ke Yi, Zengke Liu, Jianwei Zhang, Chengyuan Li, Tong Zhang

Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features

Daeho Um, Yoonji Lee, Jiwoong Park, Seulki Park, Yuneil Yeo

Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models

Hualin Zhang, Haozhen Zhang, Zhekai Liu, Bin Gu, Yi Chang

Emergence of a High-Dimensional Abstraction Phase in Language Transformers

Emily Cheng, Diego Doimo, Corentin Kervadec, Iuri Macocco, Lei Yu

Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement

Yuhang Li, Zhuying Li, Yuheng Jia

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model

Jiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

Megh Shukla, Aziz Shameem, Mathieu Salzmann, Alexandre Alahi

Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models

Shaotian Yan, Chen Shen, Wenxiao Wang, Liang Xie, Junjie Liu

Why Does the Effective Context Length of LLMs Fall Short?

Chenxin An, Jun Zhang, Ming Zhong, Lei Li, Shansan Gong

Training on the Test Task Confounds Evaluation and Emergence

Ricardo Dominguez-Olmedo, Florian E. Dorner, Moritz Hardt

Spreading Out-of-Distribution Detection on Graphs

Daeho Um, Jongin Lim, Sunoh Kim, Yuneil Yeo, Yoonho Jung

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

Qijun Gan, Song Wang, Shengtao Wu, Jianke Zhu

When Attention Sink Emerges in Language Models: An Empirical View

Xiangming Gu, Tianyu Pang, Chao Du, Qian Liu, Fengzhuo Zhang

Inverse Constitutional AI: Compressing Preferences into Principles

Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Samuel Albanie, Robert D. Mullins

PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration

Yuxuan Sun, Yunlong Zhang, Yixuan Si, Chenglu Zhu, Kai Zhang

Attribute-based Visual Reprogramming for Vision-Language Models

Chengyi Cai, Zesheng Ye, Lei Feng, Jianzhong Qi, Feng Liu

Rethinking Multiple-Instance Learning From Feature Space to Probability Space

Zhaolong Du, Shasha Mao, Xuequan Lu, MengNan Qi, Yimeng Zhang

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Xiao Liu, Tianjie Zhang, Yu Gu, Iat Long Iong, Song XiXuan

The Computational Complexity of Positive Non-Clashing Teaching in Graphs

Robert Ganian, Liana Khazaliya, Fionn Mc Inerney, Mathis Rocton

RegMix: Data Mixture as Regression for Language Model Pre-training

Qian Liu, Xiaosen Zheng, Niklas Muennighoff, Guangtao Zeng, Longxu Dou

Long-time asymptotics of noisy SVGD outside the population limit

Victor Priser, Pascal Bianchi, Adil SALIM

Physics-aligned field reconstruction with diffusion bridge

Zeyu Li, Hongkun Dou, Shen Fang, Wang Han, Yue Deng

SELF-EVOLVED REWARD LEARNING FOR LLMS

Chenghua Huang, Zhizhen Fan, Lu Wang, Fangkai Yang, Pu Zhao

PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders

Tianyu Xie, Harry Richman, Jiansi Gao, Frederick A Matsen, Cheng Zhang

Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching

Zijing Ou, Mingtian Zhang, Andi Zhang, Tim Z. Xiao, Yingzhen Li

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them

Anh Tuan Bui, Thuy-Trang Vu, Long Tung Vuong, Trung Le, Paul Montague

Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps

Han Wang, Yilin Zhao, Dian Li, Xiaohan Wang, sinbadliu

A Conditional Independence Test in the Presence of Discretization

Boyang Sun, Yu Yao, Guang-Yuan Hao, Yumou Qiu, Kun Zhang

Finding Shared Decodable Concepts and their Negations in the Brain

Cory Daniel Efird, Alex Murphy, Joel Zylberberg, Alona Fyshe

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction

Lu Dai, Yijie Xu, Jinhui Ye, Hao Liu, Hui Xiong

Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders

Qichao Shentu, Beibu Li, KAI ZHAO, Yang Shu, Zhongwen Rao

Vision and Language Synergy for Rehearsal Free Continual Learning

Muhammad Anwar Ma'sum, Mahardhika Pratama, Savitha Ramasamy, Lin Liu, H Habibullah

Centrality-guided Pre-training for Graph

Bin Liang, Shiwei Chen, Lin Gui, Hui Wang, Yue Yu

Aligning Human Motion Generation with Human Perceptions

Haoru Wang, Wentao Zhu, Luyi Miao, Yishu Xu, Feng Gao

QuaDiM: A Conditional Diffusion Model For Quantum State Property Estimation

Yehui Tang, Mabiao Long, Junchi Yan

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

Fanhu Zeng, Zhen Cheng, Fei Zhu, Hongxin Wei, Xu-yao Zhang

Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck

SHUAI ZHANG, Junfeng Fang, Xuqiang Li, Hongxin Xiang, ALAN XIA

Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design

Melis Ilayda Bal, Pier Giuseppe Sessa, Mojmir Mutny, Andreas Krause

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

Minghao Xu, Yunteng Geng, Yihang Zhang, Ling Yang, Jian Tang

Federated Few-Shot Class-Incremental Learning

Muhammad Anwar Ma'sum, Mahardhika Pratama, Lin Liu, H Habibullah, Ryszard Kowalczyk

Precedence-Constrained Winter Value for Effective Graph Data Valuation

Hongliang Chi, Wei Jin, Charu C. Aggarwal, Yao Ma

BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics

Lukas Rauch, Raphael Schwinger, Moritz Wirth, René Heinrich, Denis Huseljic

DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation

Hanbo Cheng, Limin Lin, Chenyu Liu, Pengcheng Xia, Pengfei Hu

Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach

Sinan Fan, Liang Xie, Chen Shen, Ge Teng, Xiaosong Yuan

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

Tudor Ioan Cebere, Aurélien Bellet, Nicolas Papernot

IDInit: A Universal and Stable Initialization Method for Neural Network Training

Yu Pan, Chaozheng Wang, Zekai Wu, Qifan Wang, Min Zhang

A-Bench: Are LMMs Masters at Evaluating AI-generated Images?

Zicheng Zhang, Haoning Wu, Chunyi Li, Yingjie Zhou, Wei Sun

Towards Understanding the Universality of Transformers for Next-Token Prediction

Michael Eli Sander, Gabriel Peyré

PETRA: Parallel End-to-end Training with Reversible Architectures

Stephane Rivaud, Louis Fournier, Thomas Pumir, Eugene Belilovsky, Michael Eickenberg