About Me
Hi! I'm Wei Xiao (肖巍). I will join Fudan University & Shanghai Innovation Institute as a PhD student advised by Li Zhang this fall. I am also collaborating with Yao (Mark) Mu. Previously, I gained valuable research experience in reinforcement learning and embodied intelligence at ScaleLab@SJTU and MiLab@Westlake. I got my B.Eng in Automation from Xiamen University advised by Qifeng Zhou.
My research goal is to build end-to-end general robotic system that surpasses human abilities. I think reinforcement learning and a scalable learning paradigm (e.g. World Model, Unsupervised/Self-supervised Learning) that do not mainly rely on human prior (e.g. teleoperation) are necessary for it.
I'm currently focusing on reinforcement learning of robotic foundation model (VLA) and interning at XPENG Robotics. Please drop me an email if you are interested in my research or just want to chat! Email: xiaowei2002103@foxmail.com
News
- 2026.1: 🎉 KORR and TrajBooster are accepted by ICRA2026, congrats to Jeffrey and Jiacheng！
- 2025.7: ⭐ A summary of VLA+RL - Awesome-VLA-RL - is available in Github.
- 2025.5: 🎉 Our works PORL and LIT are available in arxiv.
- 2024.11: 🎉 Homepage has been set up.
- 2024.09: 🎉 Our paper PT4Rec is accepted by ACML2024 and Machine Learning Journal.
Publications
Embodied AI & RL
Efficient Online RL Fine-Tuning with Offline Pre-trained Policy Only
Wei Xiao*, Jiacheng Liu, Zifeng Zhuang, Runze Suo, Shangke Lyu†, Donglin Wang†
Preprint
arxiv
Learning Robotic Policy with Imagined Transition: Mitigating the Trade-off between Robustness and Optimality
Wei Xiao*, Shangke Lyu†, Zhefei Gong, Renjie Wang, Donglin Wang†
Preprint
arxiv / video
Robust Online Residual Refinement via Koopman-Guided Dynamics Modeling
Zhefei Gong, Shangke Lyu, Pengxiang Ding, Wei Xiao, Donglin Wang†
IEEE International Conference on Robotics and Automation (ICRA), 2026
arxiv
TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning
Jiacheng Liu*, Pengxiang Ding*, Qihang Zhou, Yuxuan Wu, Da Huang, Zimian Peng, Wei Xiao, Weinan Zhang, Lixin Yang, Cewu Lu†, Donglin Wang†
IEEE International Conference on Robotics and Automation (ICRA), 2026
arxiv / code
Integrating Trajectory Optimization and Reinforcement Learning for Quadrupedal Jumping with Terrain-Adaptive Landing
Renjie Wang*, Shangke Lyu†, Xin Lang, Wei Xiao, Donglin Wang†
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025 (Oral)
arxiv
Recommender System
Continuous-Time Sequential Recommendation with State Space Models
Wei Xiao*, Huiying Wang*, Qifeng Zhou†, Qing Wang
Preprint
arxiv / code
PT4Rec: A Universal Prompt-Tuning Framework for Graph Contrastive Learning-Based Recommendations
Wei Xiao*, Qifeng Zhou†
Asian Conference on Machine Learning (ACML), 2024; Machine Learning journal
paper / code
Honors and Awards
Tencent Kaiwu Reinforcement Learning Competition
Team: 南强至善 — Wei Xiao*, Yifan Lin, Jinyang Lai, Huaming Xu, Zejie Jiang, Yunlong Liu†
Fourth Place (with Bonus ￥20,000) — 2023.12
leaderboard
- The 13th Mathorcup Mathematical Modelling Competition, Third prize.
- Huawei Software Elite Challenge, Third Prize.
- National Mathematical Modelling Competition for College Students, Second Prize in Fujian Province.
- National Algorithm Competition for College Students, Excellence Award.
- and so on.
