ICML 2025 Conference Submissions

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
Yongcan Yu, Yanbo Wang, Ran He, Jian Liang
- 09 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Rethinking Time Encoding via Learnable Transformation Functions
Xi Chen, Yateng Tang, Jiarong Xu, Jiawei Zhang, Siwei Zhang, Sijia Peng, Xuehao Zheng, Yun Xiong
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Delta Decompression for MoE-based LLMs Compression
Hao Gu, Wei Li, Lujun Li, Zhu Qiyuan, Mark G. Lee, Shengjie Sun, Wei Xue, Yike Guo
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition
Wei Li, Lujun Li, Hao Gu, You-Liang Huang, Mark G. Lee, Shengjie Sun, Wei Xue, Yike Guo
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
Haoquan Fang, Markus Grotz, Wilbert Pumacay, Yi Ru Wang, Dieter Fox, Ranjay Krishna, Jiafei Duan
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
COExpander: Adaptive Solution Expansion for Combinatorial Optimization
Jiale Ma, Wenzheng Pan, Yang Li, Junchi Yan
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
BECAME: Bayesian Continual Learning with Adaptive Model Merging
Mei Li, Yuxiang Lu, Qinyan Dai, Suizhi Huang, Yue Ding, Hongtao Lu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Targeted control of fast prototyping through domain-specific interface
Yu-Zhe Shi, Mingchen Liu, Hanlu Ma, Qiao Xu, Huamin Qu, Kun He, Lecheng Ruan, Qining Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Conditional Lagrangian Wasserstein Flow for Time Series Imputation
Weizhu Qian, Dalin Zhang, Yan Zhao, Yunyao Cheng
- 09 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
Weizhong Huang, Yuxin Zhang, Xiawu Zheng, Fei Chao, Rongrong Ji
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization
Dasol Hong, Wooju Lee, Hyun Myung
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Vision Graph Prompting via Semantic Low-Rank Decomposition
Zixiang Ai, Zichen Liu, Jiahuan Zhou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
Zixiang Ai, Zichen Liu, Yuanhang Lei, Zhenyu Cui, Xu Zou, Jiahuan Zhou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Token Coordinated Prompt Attention is Needed for Visual Prompting
Zichen Liu, Xu Zou, Gang Hua, Jiahuan Zhou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Componential Prompt-Knowledge Alignment for Domain Incremental Learning
Kunlun Xu, Xu Zou, Gang Hua, Jiahuan Zhou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Off-Policy Evaluation of Ranking Policies for Large Action Spaces via Embeddings and User Behavior Assumption
Tatsuki Takahashi, Chihiro Maru, Hiroko Shoji
- 09 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination
Yifan Sun, Han Wang, Dongbai Li, Gang Wang, Huan Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
Wonkwang Lee, Jongwon Jeong, Taehong Moon, Hyeon-Jong Kim, Jaehyeon Kim, Gunhee Kim, Byeong-Uk Lee
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Teaching Physical Awareness to LLMs through Sounds
Weiguo Wang, Andy Nie, Wenrui Zhou, Yi Kai, Chengchen Hu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images
Zhengrui Guo, Qichen Sun, Jiabo MA, Lishuang Feng, Jinzhuo Wang, Hao Chen
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Sub-Sequential Physics-Informed Learning with State Space Model
Chenhui Xu, Dancheng Liu, Yuting Hu, Jiajie Li, Ruiyang Qin, Qingxiao Zheng, Jinjun Xiong
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Policy Filtration for RLHF to Mitigate Noise in Reward Models
Chuheng Zhang, Wei Shen, Li Zhao, Xuyun Zhang, Xiaolong Xu, Wanchun Dou, Jiang Bian
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone