Yihao Sun

PhD student, Mila - Quebec Artificial Intelligence Institute

Joined

October 2022

Names

Yihao Sun (Preferred)

Emails

****@lamda.nju.edu.cn (Confirmed)

****@mila.quebec (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

PhD student

Mila - Quebec Artificial Intelligence Institute (mila.quebec)

2025 – Present

MS student

nanjing university (nju.edu.cn)

2021 – 2024

Undergrad student

Sichuan University (scu.edu.cn)

2017 – 2021

Advisors, Relations & Conflicts

Coauthor

Yang Yu

Present

PhD Advisor

Pierre-Luc Bacon

Present

Coauthor

Haoxin Lin

Present

Coauthor

Zhilong Zhang

Present

Expertise

Reinforcement Learning

Present

Publications

Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
Zhichao Wu, Junyin Ye, Zhilong Zhang, Yihao Sun, Haoxin Lin, Haoxiang Ren, Jiaheng Luo, Lei Yuan, Yang Yu
- ICLR 2026 Workshop World Models
- Readers: Everyone
Planning with Unified Multimodal Models
Yihao Sun, Zhilong Zhang, Yang Yu, Pierre-Luc Bacon
- ICLR 2026 Workshop World Models
- Readers: Everyone
Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
Zhilong Zhang, Haoxiang Ren, Yihao Sun, Yifei Sheng, Haonan Wang, Zhichao Wu, Haoxin Lin, Pierre-Luc Bacon, Yang Yu
- ICLR 2026 Workshop World Models
- Readers: Everyone
Hierarchical Value-Decomposed Offline Reinforcement Learning for Whole-Body Control
Zhilong Zhang, Yunpeng Mei, Xinghao Du, Hongjie Cao, Haonan Wang, Pengyuan Min, Chenyu Wang, Pengfei Chen, Chenbo Xin, Yijie Wang, Wenyu Luo, Yihao Sun, Yidi Wang, Lei Yuan, Gang Wang, Yang Yu
- ICLR 2026 Poster
- Readers: Everyone
On the Representation Degradation in Vision-Language-Action Models
Zhilong Zhang, Xiong-Hui Chen, Yidi Wang, Yihao Sun, Wenyu Luo, Haoxiang Ren, Haoxin Lin, Yang Yu
- Submitted to ICLR 2026
- Readers: Everyone
ADM-v2: Pursuing Full-Horizon Roll-out in Dynamics Models for Offline Policy Learning and Evaluation
Haoxin Lin, Siyuan Xiao, Yi-Chen Li, Zhilong Zhang, Yihao Sun, Chengxing Jia, Yang Yu
- ICLR 2026 Poster
- Readers: Everyone
Planning with Unified Multimodal Models
Yihao Sun, Zhilong Zhang, Yang Yu, Pierre-Luc Bacon
- Submitted to ICLR 2026
- Readers: Everyone
The Three Regimes of Offline-to-Online Reinforcement Learning
Lu Li, Tianwei Ni, Yihao Sun, Pierre-Luc Bacon
- Submitted to ICLR 2026
- Readers: Everyone
WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making
Zhilong Zhang, Ruifeng Chen, Junyin Ye, Yihao Sun, Haoxiang Ren, Xinghao Du, Pengyuan Wang, Jing-Cheng Pang, Kaiyuan Li, Tian-Shuo Liu, Haoxin Lin, Yang Yu, Zhi-Hua Zhou
- NeurIPS 2025 Workshop EWM
- Readers: Everyone
Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
Zhilong Zhang, Tian Xu, Xinghao Du, Xingchen Cao, Yihao Sun, Yang Yu
- ICML 2025 poster
- Readers: Everyone

View all 22 publications

Co-Authors

View all 46 co-authors