ICLR 2025

3,703 papers

W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models

Shang Wang

Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

Simiao Li, Yun Zhang, Wei Li, Hanting Chen, Wenjia Wang

Deconstructing Denoising Diffusion Models for Self-Supervised Learning

Xinlei Chen, Zhuang Liu, Saining Xie, Kaiming He

SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

Zhenyu Yang, Yuhang Hu, Zemin Du, Dizhan Xue, Shengsheng Qian

Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games

Yanzheng Chen, Jun Yu

qNBO: quasi-Newton Meets Bilevel Optimization

Sheng Fang, Yongjin Liu, Wei Yao, Chengming Yu, Jin Zhang

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

Yun Zhang, Wei Li, Simiao Li, Hanting Chen, Zhijun Tu

Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series Forecasting

Qi Li, Zhenyu Zhang, Lei Yao, Zhaoxia Li, Tianyi Zhong

SIMPL: Scalable and hassle-free optimisation of neural representations from behaviour

Tom George, Pierre Glaser, Kim Stachenfeld, Caswell Barry, Claudia Clopath

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing

Elad Romanov, Fangzhao Zhang, Mert Pilanci

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora

Advantage-Guided Distillation for Preference Alignment in Small Language Models

Shiping Gao, Fanqi Wan, Jiajian Guo, Xiaojun Quan, Qifan Wang

Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions

Wei Yao, Haian Yin, Shangzhi Zeng, Jin Zhang

Uncovering Overfitting in Large Language Model Editing

Mengqi Zhang, Xiaotian Ye, Qiang Liu, Shu Wu, Pengjie Ren

Generating Likely Counterfactuals Using Sum-Product Networks

Jiří Němeček, Tomas Pevny, Jakub Marecek

Multi-Dimensional Conformal Prediction

Yam Tawachi, Bracha Laufer-Goldshtein

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang

Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data

Seiji Maekawa, Hayate Iso, Nikita Bhutani

BANGS: Game-theoretic Node Selection for Graph Self-Training

Fangxin Wang, Kay Liu, Sourav Medya, Philip S. Yu

Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off

Futa Kai Waseda, Ching-Chun Chang, Isao Echizen

Bridging the Gap between Database Search and \emph{De Novo} Peptide Sequencing with SearchNovo

Jun Xia, Sizhe Liu, Jingbo Zhou, Shaorong Chen, Hongxin Xiang

How Far Are We from True Unlearnability?

Kai Ye, Liangcai Su, Chenxiong Qian

Towards a Complete Logical Framework for GNN Expressiveness

Tuo Xu

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Alexander Nikulin, Ilya Zisman, Alexey Zemtsov, Vladislav Kurenkov

Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks

Hanling Tian, Yuhang Liu, Mingzhen He, Zhengbao He, Zhehao Huang

Designing Mechanical Meta-Materials by Learning Equivariant Flows

Mehran Mirramezani, Anne S. Meeussen, Katia Bertoldi, Peter Orbanz, Ryan P Adams

Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement

Xueyao Zhang, XiaoHui Zhang, Kainan Peng, Zhenyu Tang, Vimal Manohar

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Terry Yue Zhuo, Vu Minh Chien, Jenny Chim, Han Hu, Wenhao Yu

Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models

Hanzhu Chen, Xu Shen, Jie Wang, Zehao Wang, Qitan Lv

BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

Hikaru Shindo, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting

Lines of Thought in Large Language Models

Raphaël Sarfati, Toni J.b. Liu, Nicolas Boulle, Christopher Earls

miniCTX: Neural Theorem Proving with (Long-)Contexts

Jiewen Hu, Thomas Zhu, Sean Welleck

OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang

PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

Pablo Lemos, Sammy Nasser Sharief, Nikolay Malkin, Salma Salhi, Connor Stone

VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?

Xize Cheng, Ruofan Hu, Xiaoda Yang, Jingyu Lu, Dongjie Fu

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling

Jiawei Xu, Rui Yang, Shuang Qiu, Feng Luo, Meng Fang

Improving Large Language Model Planning with Action Sequence Similarity

Xinran Zhao, Hanie Sedghi, Bernd Bohnet, Dale Schuurmans, Azade Nova

HGM³: Hierarchical Generative Masked Motion Modeling with Hard Token Mining

Minjae Jeong, Yechan Hwang, Jaejin Lee, Sungyoon Jung, Won Hwa Kim

Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

Mingfei Han, Linjie Yang, Xiaojun Chang, Lina Yao, Heng Wang

Efficient Model Editing with Task-Localized Sparse Fine-tuning

Leonardo Iurada, Marco Ciccone, Tatiana Tommasi

Small Models are LLM Knowledge Triggers for Medical Tabular Prediction

Jiahuan Yan, Jintai Chen, Chaowen Hu, Bo Zheng, Yaojun Hu

Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Jason Ramapuram, Federico Danieli, Eeshan Gunesh Dhekane, Floris Weers, Dan Busbridge

Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming

Haoyang Liu, Jie Wang, Zijie Geng, Xijun Li, Yuxuan Zong

PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos

Alex N Wang, Christopher Hoang, Yuwen Xiong, Yann LeCun, Mengye Ren

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient

Wenlong Wang, Ivana Dusparic, Yucheng Shi, Ke ZHANG, Vinny Cahill

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Anthony GX-Chen, Kenneth Marino, Rob Fergus

ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition

Joseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah

UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate

Julián Tachella, Mike Davies, Laurent Jacques

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

Xingrun Xing, Boyan Gao, Zheng Liu, David A. Clifton, Shitao Xiao

DICE: Data Influence Cascade in Decentralized Learning

Tongtian Zhu, Wenhao Li, Can Wang, Fengxiang He

Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport

Siqi Zeng, Sixian Du, Makoto Yamada, Han Zhao

Model Equality Testing: Which Model is this API Serving?

Irena Gao, Percy Liang, Carlos Guestrin

Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs

Yuzhou Chen, Yulia Gel

How efficient is LLM-generated code? A rigorous & high-standard benchmark

Ruizhong Qiu, Weiliang Will Zeng, James Ezick, Christopher Lott, Hanghang Tong

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection

Yun Zhu, Jia-Chen Gu, Caitlin Sikora, Ho Ko, Yinxiao Liu

LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation

Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

Muhammed Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Marco Mondelli, Samet Oymak

Language-Assisted Feature Transformation for Anomaly Detection

Eunggu Yun, Heonjin Ha, Yeongwoo Nam, Bryan Dongik Lee

Diversity-Rewarded CFG Distillation

Geoffrey Cideron, Andrea Agostinelli, Johan Ferret, Sertan Girgin, Romuald Elie

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

Boyang Zheng, Chumeng Liang, Xiaoyu Wu

Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods

Hossein Taheri, CHRISTOS THRAMPOULIDIS, Arya Mazumdar

SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes

Tony Alex, Sara Atito, Armin Mustafa, Muhammad Awais, Philip J B Jackson

Generalized Principal-Agent Problem with a Learning Agent

Tao LIN, Yiling Chen

Reassessing How to Compare and Improve the Calibration of Machine Learning Models

Muthu Chidambaram, Rong Ge

Streaming Algorithms For ℓ_p Flows and ℓ_p Regression

Amit Chakrabarti, Jeffrey Jiang, David Woodruff, Taisuke Yasuda

Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen

Alessandro Palma, Till Richter, Hanyi Zhang, Manuel Lubetzki, Alexander Tong

On the Completeness of Invariant Geometric Deep Learning Models

Zian Li, Xiyuan Wang, Shijia Kang, Muhan Zhang

VideoPhy: Evaluating Physical Commonsense for Video Generation

Hritik Bansal, Zongyu Lin, Tianyi Xie, Zeshun Zong, Michal Yarom

Computing Circuits Optimization via Model-Based Circuit Genetic Evolution

Zhihai Wang, Jie Wang, Xilin Xia, Dongsheng Zuo, Lei Chen

LaMPlace: Learning to Optimize Cross-Stage Metrics in Macro Placement

Zijie Geng, Jie Wang, Ziyan Liu, Siyuan Xu, Zhentao Tang

GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs

Kalliopi Basioti, Pritish Sahu, Tony Qingze Liu, Zihao Xu, Hao Wang

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke, Xuan-Phi Nguyen

BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

Yu Feng, Ben Zhou, Weidong Lin, Dan Roth

Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models

Jun Luo, Chen Chen, Shandong Wu

Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Shansan Gong, Shivam Agarwal, Yizhe Zhang, Jiacheng Ye, Lin Zheng

Adaptive Length Image Tokenization via Recurrent Allocation

Shivam Duggal, Phillip Isola, Antonio Torralba, William T. Freeman

Differentiable Integer Linear Programming

Zijie Geng, Jie Wang, Xijun Li, Fangzhou Zhu, Jianye Hao

Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs

Shane Bergsma, Nolan Simran Dey, Gurpreet Gosal, Gavia Gray, Daria Soboleva

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

Yarden As, Bhavya Sukhija, Lenart Treven, Carmelo Sferrazza, Stelian Coros

Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

Han Lin, Jaemin Cho, Abhay Zala, Mohit Bansal

LevAttention: Time, Space and Streaming Efficient Algorithm for Heavy Attentions

Ravindran Kannan, Chiranjib Bhattacharyya, Praneeth Kacham, David Woodruff

Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks

Simon Heilig, Alessio Gravina, Alessandro Trenta, Claudio Gallicchio, Davide Bacciu

A Transfer Attack to Image Watermarks

Yuepeng Hu, Zhengyuan Jiang, Moyang Guo, Neil Zhenqiang Gong

Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems

Jindong Tian, Yuxuan Liang, Ronghui Xu, Peng Chen, Chenjuan Guo

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Weijia Shi, Jaechan Lee, Yangsibo Huang, Sadhika Malladi, Jieyu Zhao

Composable Interventions for Language Models

Arinbjörn Kolbeinsson, Kyle O'Brien, Tianjin Huang, Shanghua Gao, Shiwei Liu

Generative Monoculture in Large Language Models

Fan Wu, Emily Black, Varun Chandrasekaran

Training Robust Ensembles Requires Rethinking Lipschitz Continuity

Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran

BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities

Shaozhe Hao, Xuantong Liu, Xianbiao Qi, Shihao Zhao, Bojia Zi

Sparse Autoencoders Do Not Find Canonical Units of Analysis

Patrick Leask, Bart Bussmann, Michael T Pearce, Joseph Isaac Bloom, Curt Tigges

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling

David Grangier, Simin Fan, Skyler Seto, Pierre Ablin

Autoregressive Pretraining with Mamba in Vision

Sucheng Ren, Xianhang Li, Haoqin Tu, Feng Wang, Fangxun Shu

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat, Yuandong Tian, Qinqing Zheng

Human-Aligned Chess With a Bit of Search

Yiming Zhang, Athul Paul Jacob, Vivian Lai, Daniel Fried, Daphne Ippolito

The Superposition of Diffusion Models Using the Itô Density Estimator

Marta Skreta, Lazar Atanackovic, Joey Bose, Alexander Tong, Kirill Neklyudov

Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning

Berken Utku Demirel, Christian Holz

On Speeding Up Language Model Evaluation

Jin Peng Zhou, Christian K Belardi, Ruihan Wu, Travis Zhang, Carla P Gomes

Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling

Wei Guo, Molei Tao, Yongxin Chen

Distance-Based Tree-Sliced Wasserstein Distance

Hoang V. Tran, Minh-Khoi Nguyen-Nhat, Huyen Trang Pham, Thanh Chu, Tam Le

SGD with memory: fundamental properties and stochastic acceleration

Dmitry Yarotsky, Maksim Velikanov