ICLR 2025

3,703 papers

Monitoring Latent World States in Language Models with Propositional Probes

Jiahai Feng, Stuart Russell, Jacob Steinhardt

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaojian Ma, Tao Yuan

Rationalizing and Augmenting Dynamic Graph Neural Networks

Guibin Zhang, Yiyan Qi, Ziyang Cheng, Yanwei Yue, Dawei Cheng

Compositional Entailment Learning for Hyperbolic Vision-Language Models

Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, Fabio Galasso

MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

Peng Jin, Bo Zhu, Li Yuan, Shuicheng Yan

Regularization by Texts for Latent Diffusion Inverse Solvers

Jeongsol Kim, Geon Yeong Park, Hyungjin Chung, Jong Chul Ye

Preference Optimization for Reasoning with Pseudo Feedback

Fangkai Jiao, Geyang Guo, Xingxing Zhang, Nancy F. Chen, Shafiq Joty

Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Chunting Zhou, LILI YU, Arun Babu, Kushal Tirumala, Michihiro Yasunaga

QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing

Grace Zhang, Ayush Jain, Injune Hwang, Shao-Hua Sun, Joseph J Lim

Real-Time Video Generation with Pyramid Attention Broadcast

Xuanlei Zhao, Xiaolong Jin, Kai Wang, Yang You

LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak Supervision

Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim

Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving

Kairui Yang, Zihao Guo, Gengjie Lin, Haotian Dong, Zhao Huang

Tight Clusters Make Specialized Experts

Stefan Nielsen, Rachel Teo, Laziz Abdullaev, Tan Minh Nguyen

Investigating Pattern Neurons in Urban Time Series Forecasting

Chengxin Wang, Yiran Zhao, Shaofeng Cai, Gary Tan

Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model

Long Le, Jason Xie, William Liang, Hung-Ju Wang, Yue Yang

TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation

Chenghan Li, Mingchen Li, Ruisheng Diao

Large Convolutional Model Tuning via Filter Subspace

Wei Chen, Zichen Miao, Qiang Qiu

Exploring the Camera Bias of Person Re-identification

Myungseo Song, Jin-Woo Park, Jong-Seok Lee

Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives

Zeliang Zhang, Susan Liang, Daiki Shimada, Chenliang Xu

Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene

Jiahao Wu, Rui Peng, Zhiyan Wang, Lu Xiao, Luyang Tang

Adaptive Camera Sensor for Vision Models

Eunsu Baek, Sung-hwan Han, Taesik Gong, Hyung-Sin Kim

Segment Any 3D Object with Language

Seungjun Lee, Yuyang Zhao, Gim Hee Lee

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

Mengxuan Hu, Zihan Guan, Yi Zeng, Junfeng Guo, Zhongliang Zhou

Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models

Qingni Wang, Tiantian Geng, Zhiyuan Wang, Teng Wang, Bo Fu

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming

Yukun Chen, Shuo Shao, Enhao Huang, Yiming Li, Pin-Yu Chen

3D Vision-Language Gaussian Splatting

Qucheng Peng, Benjamin Planche, Zhongpai Gao, Meng Zheng, Anwesa Choudhuri

Trusted Multi-View Classification via Evolutionary Multi-View Fusion

Xinyan Liang, Pinhan Fu, Yuhua Qian, Qian Guo, Guoqing Liu

Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models

Yong-Hyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Yuki Mitsufuji

SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction

Yang Zhou, Hao Shao, Letian Wang, Steven L. Waslander, hongsheng Li

Transformer Meets Twicing: Harnessing Unattended Residual Information

Laziz Abdullaev, Tan Minh Nguyen

Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection

Chuhan Zhang, Chaoyang Zhu, Pingcheng Dong, Long Chen, Dong Zhang

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

Gaojie Lin, Jianwen Jiang, Chao Liang, Tianyun Zhong, Jiaqi Yang

HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded Scenes

Xin lin, Shi Luo, Xiaojun Shan, Xiaoyu Zhou, Chao Ren

OS-ATLAS: Foundation Action Model for Generalist GUI Agents

Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun

When Graph Neural Networks Meet Dynamic Mode Decomposition

Dai Shi, Lequan Lin, Andi Han, Zhiyong Wang, Yi Guo

Student-Informed Teacher Training

Nico Messikommer, Jiaxu Xing, Elie Aljalbout, Davide Scaramuzza

Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes

Jongmin Lee, Ernest K. Ryu

Spurious Forgetting in Continual Learning of Language Models

Junhao Zheng, Xidi Cai, Shengjie Qiu, Qianli Ma

TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram

Mingxi Lei, Chunwei Ma, Meng Ding, Yufan Zhou, Ziyun Huang

Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning

Minheng Ni, YuTao Fan, Lei Zhang, Wangmeng Zuo

MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation

Siyi Jiao, Wenzheng Zeng, Yerong Li, Huayu Zhang, Changxin Gao

Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow Scheduling

Yifan Yang, Gang Chen, Hui Ma, Cong Zhang, Zhiguang Cao

Text-to-Image Rectified Flow as Plug-and-Play Priors

Xiaofeng Yang, Chen Cheng, Xulei Yang, Fayao Liu, Guosheng Lin

PaCA: Partial Connection Adaptation for Efficient Fine-Tuning

Sunghyeon Woo, Sol Namkung, Sunwoo Lee, Inho Jeong, Beomseok Kim

Multimodal Situational Safety

Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao, Anderson Compalas, Dawn Song

Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning

Yunyue Wei, Shanning Zhuang, Vincent Zhuang, Yanan Sui

Improving Unsupervised Constituency Parsing via Maximizing Semantic Information

Junjie Chen, Xiangheng He, Yusuke Miyao, Danushka Bollegala

Wasserstein-Regularized Conformal Prediction under General Distribution Shift

Rui Xu, Chao Chen, Yue Sun, Parvathinathan Venkitasubramaniam, Sihong Xie

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang

Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across Domains

Razmik Arman Khosrovian, Takaharu Yaguchi, Hiroaki Yoshimura, Takashi Matsubara

Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions

Xiaoran Jiao, Weian Mao, Wengong Jin, Peiyuan Yang, Hao Chen

Enhancing Prediction Performance through Influence Measure

Shuguang Yu, Wenqian Xu, Xinyi Zhou, Xuechun Wang, Hongtu Zhu

Unsupervised Meta-Learning via In-Context Learning

Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren, Marlena Nowaczyk

Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

Jianwen Jiang, Chao Liang, Jiaqi Yang, Gaojie Lin, Tianyun Zhong

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation

Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang

From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ

Zhaojing Wen, Qiulin Zhang, yuan zhang, Rudan Chen, Xichao Yang

Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness

Xianglu Wang, Hu Ding

Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance Satisfaction

Liangliang Shi, Yufeng Li, Kaipeng Zeng, Yihui Tu, Junchi Yan

AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors

Ruoxuan Feng, Jiangyu Hu, Wenke Xia, TianciGao, Ao Shen

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li

Direct Distributional Optimization for Provable Alignment of Diffusion Models

Ryotaro Kawata, Kazusato Oko, Atsushi Nitanda, Taiji Suzuki

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL

Ghada Sokar, Johan Samir Obando Ceron, Aaron Courville, Hugo Larochelle, Pablo Samuel Castro

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization

Shuang Liu, Yihan Wang, Yifan Zhu, yibo miao, Xiao-Shan Gao

Following the Human Thread in Social Navigation

Luca Scofano, Alessio Sampieri, Tommaso Campari, Valentino Sacco, Indro Spinelli

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

Xiangyu Zhao, Zhiwang Zhou, zhangwenlong, Yihao Liu, Xiangyu Chen

A Multiscale Frequency Domain Causal Framework for Enhanced Pathological Analysis

Xiaoyu Cui, Weixing Chen, Jiandong Su

Unifying Causal Representation Learning with the Invariance Principle

Dingling Yao, Dario Rancati, Riccardo Cadei, Marco Fumero, Francesco Locatello

A General Framework for Producing Interpretable Semantic Text Embeddings

Yiqun Sun, Qiang Huang, Yixuan Tang, Anthony Kum Hoe Tung, Jun Yu

Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction

Zilin Fang, David Hsu, Gim Hee Lee

Discrete Latent Plans via Semantic Skill Abstractions

Haobin Jiang, Jiangxing Wang, Zongqing Lu

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

Bai LiChen, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu

Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

Qining Zhang, Lei Ying

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

Yuto Nishimura, Takumi Hirose, Masanari Ohi, Hideki Nakayama, Nakamasa Inoue

Mechanistic Permutability: Match Features Across Layers

Nikita Balagansky, Ian Maksimov, Daniil Gavrilov

Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning

Chongjie Si, Xuehui Wang, Xue Yang, Zhengqin Xu, Qingyun Li

Transformer-Squared: Self-adaptive LLMs

Qi Sun, Edoardo Cetin, Yujin Tang

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

Khanh Nguyen, Raouf Kerkouche, Mario Fritz, Dimosthenis Karatzas

Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages

Zui Chen, Tianqiao Liu, Tongqing, Mi Tian, Weiqi Luo

AutoUAD: Hyper-parameter Optimization for Unsupervised Anomaly Detection

Wei Dai, Jicong Fan

Layerwise Recurrent Router for Mixture-of-Experts

Zihan Qiu, Zeyu Huang, Shuang Cheng, Yizhi Zhou, Zili Wang

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh

Deep Kernel Relative Test for Machine-generated Text Detection

Yiliao Song, Zhenqiao Yuan, Shuhai Zhang, Zhen Fang, Jun Yu

On the Feature Learning in Diffusion Models

Andi Han, Wei Huang, Yuan Cao, Difan Zou

Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization

Hao Dong, Eleni Chatzi, Olga Fink

Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning

Lequan Lin, Dai Shi, Andi Han, Zhiyong Wang, Junbin Gao

Text4Seg: Reimagining Image Segmentation as Text Generation

Mengcheng Lan, Chaofeng Chen, Yue Zhou, Jiaxing Xu, Yiping Ke

Conditional Testing based on Localized Conformal p-values

Xiaoyang Wu, Lin Lu, Zhaojun Wang, Changliang Zou

Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective

Andrew Jesson, Nicolas Beltran-Velez, David Blei

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Yaxi Lu, Shenzhi Yang, Cheng Qian, Guirong Chen, Qinyu Luo

SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation

Pengfei Chen, Lingxi Xie, Xinyue Huo, Xuehui Yu, XIAOPENG ZHANG

Co^3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion

Xingqun Qi, Yatian Wang, Hengyuan Zhang, Jiahao Pan, Wei Xue

Revolutionizing EMCCD Denoising through a Novel Physics-Based Learning Framework for Noise Modeling

Haiyang Jiang, Tetsuichi Wazawa, Imari Sato, Takeharu Nagai, Yinqiang Zheng

Trajectory attention for fine-grained video motion control

Zeqi Xiao, Wenqi Ouyang, Yifan Zhou, Shuai Yang, Lei Yang

FairDen: Fair Density-Based Clustering

Lena Krieger, Anna Beer, Pernille Matthews, Anneka Myrup Thiesson, Ira Assent

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Can Demircan, Tankred Saanum, Akshay Kumar Jagadish, Marcel Binz, Eric Schulz

DRoP: Distributionally Robust Data Pruning

Artem M Vysogorets, Kartik Ahuja, Julia Kempe

Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision

Weicai Yan, Wang Lin, Zirun Guo, Ye Wang, Fangming Feng

RGB-Event ISP: The Dataset and Benchmark

Yunfan Lu, Yanlin Qian, Ziyang Rao, Junren Xiao, Liming Chen

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning

Jiacheng Ye, Jiahui Gao, Shansan Gong, Lin Zheng, Xin Jiang

Implicit Search via Discrete Diffusion: A Study on Chess

Jiacheng Ye, Zhenyu Wu, Jiahui Gao, Zhiyong Wu, Xin Jiang