Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
In Forty-third International Conference on Machine Learning (ICML), 2026, 2026
Jiawei Xu and Minghui Liu and Aakriti Agrawal and Yifan Chen and Furong Huang
Publisher's website
Jiawei Xu and Minghui Liu and Aakriti Agrawal and Yifan Chen and Furong Huang
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
In Forty-third International Conference on Machine Learning (ICML), 2026, 2026
Tong Zheng and Chengsong Huang and Runpeng Dai and Yun He and Rui Liu and Xin Ni and Huiwen Bao and Kaishen Wang and Hongtu Zhu and Jiaxin Huang and Furong Huang and Heng Huang
Publisher's website
Tong Zheng and Chengsong Huang and Runpeng Dai and Yun He and Rui Liu and Xin Ni and Huiwen Bao and Kaishen Wang and Hongtu Zhu and Jiaxin Huang and Furong Huang and Heng Huang
TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
In Forty-third International Conference on Machine Learning (ICML), 2026, 2026
Fangxu Yu and Xingang Guo and Lingzhi Yuan and Haoqiang Kang and Hongyu Zhao and Lianhui Qin and Furong Huang and Bin Hu and Tianyi Zhou
Publisher's website
Fangxu Yu and Xingang Guo and Lingzhi Yuan and Haoqiang Kang and Hongyu Zhao and Lianhui Qin and Furong Huang and Bin Hu and Tianyi Zhou
MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems
In Forty-third International Conference on Machine Learning (ICML), 2026, 2026
Zachary McBride Lazri and Anirudh Nakra and Ivan Brugere and Danial Dervovic and Antigoni Polychroniadou and Furong Huang and Dana Dachman-Soled and Min Wu
Publisher's website
Zachary McBride Lazri and Anirudh Nakra and Ivan Brugere and Danial Dervovic and Antigoni Polychroniadou and Furong Huang and Dana Dachman-Soled and Min Wu
Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
In Forty-third International Conference on Machine Learning (ICML), 2026, 2026
Soumya Suvra Ghosal and Souradip Chakraborty and Vaibhav Singh and Furong Huang and Dinesh Manocha and Amrit Singh Bedi
Publisher's website
Soumya Suvra Ghosal and Souradip Chakraborty and Vaibhav Singh and Furong Huang and Dinesh Manocha and Amrit Singh Bedi
Compositional Adversarial Training for Robust Visual Watermarking
In 2nd Workshop on Compositional Learning: Safety, Interpretability, and Agents, ICML 2026, 2026
Anirudh Satheesh and Michael-Andrei Panaitescu-Liess and Andrew Ye Xu and Georgios Milis and Heng Huang and Zikui Cai and Furong Huang
Anirudh Satheesh and Michael-Andrei Panaitescu-Liess and Andrew Ye Xu and Georgios Milis and Heng Huang and Zikui Cai and Furong Huang
Token-Level LLM Collaboration via FusionRoute
In Forty-third International Conference on Machine Learning (ICML), 2026, 2026
Nuoya Xiong and Yuhang Zhou and Hanqing Zeng and Zhaorun Chen and Furong Huang and Shuchao Bi and Lizhu Zhang and Zhuokai Zhao
Publisher's website
Nuoya Xiong and Yuhang Zhou and Hanqing Zeng and Zhaorun Chen and Furong Huang and Shuchao Bi and Lizhu Zhang and Zhuokai Zhao
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
In Forty-third International Conference on Machine Learning (ICML), 2026, 2026
Udari Madhushani Sehwag and Elaine Lau and Haniyeh Ehsani Oskouie and Shayan Shabihi and Erich Liang and Andrea Sarai Echeverria Toledo and Guillermo A. Mangialardi and Sergio Fonrouge and Ed-Yeremai Hernandez-Cardona and Paula Vergara and Utkarsh Tyagi and Chen Bo Calvin Zhang and Pavi Bhatter and Nicholas E. Johnson and Furong Huang and Ernesto Gabriel Hernández Montoya and Bing Liu
Publisher's website
Udari Madhushani Sehwag and Elaine Lau and Haniyeh Ehsani Oskouie and Shayan Shabihi and Erich Liang and Andrea Sarai Echeverria Toledo and Guillermo A. Mangialardi and Sergio Fonrouge and Ed-Yeremai Hernandez-Cardona and Paula Vergara and Utkarsh Tyagi and Chen Bo Calvin Zhang and Pavi Bhatter and Nicholas E. Johnson and Furong Huang and Ernesto Gabriel Hernández Montoya and Bing Liu
Advancing Regulation in Artificial Intelligence: An Auction-Based Approach
In The Ninth Annual ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2026, 2026
Marco Bornstein and Zora Che and Suhas Julapalli and Abdirisak Mohamed and Amrit Singh Bedi and Furong Huang
Publisher's website
Marco Bornstein and Zora Che and Suhas Julapalli and Abdirisak Mohamed and Amrit Singh Bedi and Furong Huang
Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling
In Main Conference, The 64th Annual Meeting of the Association for Computational Linguistics (ACL), Oral, 2026, 2026
Pankayaraj Pathmanathan and Furong Huang
Publisher's website
Pankayaraj Pathmanathan and Furong Huang