ICML 2025 Conference Submissions

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Trustworthy Machine Learning through Data-Specific Indistinguishability
Hanshen Xiao, Zhen Yang, G. Edward Suh
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity
Yufei Huang, Changhu Wang, Junjie Tang, Weichi Wu, Ruibin Xi
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
AnalogGenie-Lite: Enhancing Scalability and Precision in Circuit Topology Discovery through Lightweight Graph Modeling
Jian Gao, Weidong Cao, Xuan Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Function-to-Style Guidance of LLMs for Code Translation
Longhui Zhang, Bin Wang, Jiahao Wang, Xiaofeng Zhao, Min Zhang, Hao Yang, Meishan Zhang, YU LI, Jing Li, Jun Yu, Min Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Agent Workflow Memory
Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models
Yangxu Liao, Wenke Huang, Guancheng Wan, Jian Liang, Bin Yang, Mang Ye
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Bayesian Active Learning for Bivariate Causal Discovery
Yuxuan Wang, Mingzhou Liu, Xinwei Sun, Wei Wang, Yizhou Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Likelihood-based Finetuning of Protein Language Models for Few-shot Fitness Prediction and Design
Alex Hawkins-Hooker, Shikha Surana, Jakub Kmec, Oliver Bent, Paul Duckworth
- 21 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Adapting Precomputed Features for Efficient Graph Condensation
Yuan Li, Jun Hu, Zemin Liu, Bryan Hooi, Jia Chen, Bingsheng He
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs
Jie Hu, Yi-Ting Ma, Do Young Eun
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
Transfer Learning for Nonparametric Contextual Dynamic Pricing
Fan Wang, Feiyu Jiang, Zifeng Zhao, Yi Yu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Learning to Quantize for Training Vector-Quantized Networks
Peijia Qin, Jianguo Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
Wonjun Lee, Doehyeon Lee, Eugene Choi, Sangyoon Yu, Ashkan Yousefpour, Haon Park, Bumsub Ham, Suhyun Kim
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Learning to Plan with Personalized Preferences
Manjie Xu, Xinyi Yang, Wei Liang, Chi Zhang, Yixin Zhu
- 21 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Discriminative Policy Optimization for Token-Level Reward Models
Hongzhan Chen, Tao Yang, Shiping Gao, Ruijun Chen, Xiaojun Quan, Hongtao Tian, Ting Yao
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero, Zohreh Shams, Mateja Jamnik
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Latent Mamba Operator for Partial Differential Equations
Karn Tiwari, Niladri Dutta, N M Anoop Krishnan, Prathosh AP
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
Angel Villar-Corrales, Sven Behnke
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
Benjamin Feuer, Chinmay Hegde
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies
Piotr Kubaty, Bartosz Wójcik, Bartłomiej Tomasz Krzepkowski, Monika Michaluk, Tomasz Trzcinski, Jary Pomponi, Kamil Adamczewski
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
am-ELO: A Stable Framework for Arena-based LLM Evaluation
Zirui Liu, Jiatong Li, Yan Zhuang, Qi Liu, Shuanghong Shen, Jie Ouyang, Mingyue Cheng, Shijin Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Adaptive Constrained Optimization for Neural Vehicle Routing
Chengrui Gao, Haopu Shang, Yuyang Jiang, Ke Xue, Chao Qian
- 21 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Daniil Laptev, Nikita Balagansky, Yaroslav Aksenov, Daniil Gavrilov
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
Jan Ludziejewski, Maciej Pióro, Jakub Krajewski, Maciej Stefaniak, Michał Krutul, Jan Małaśnicki, Marek Cygan, Piotr Sankowski, Kamil Adamczewski, Piotr Miłoś, Sebastian Jaszczur
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone