About me
Hi! I’m an undergraduate student at Shanghai Jiao Tong University.
I am deeply interested in leveraging the inherent structure of the physical world, governed by its fundamental laws, to guide and inform more efficient and generalizable approaches to learning.
Affiliations

[miHoYo]
Nov 2025 - Present
Research Scientist
Intern, Motion Generation

Shanghai Jiao Tong University
Sept 2022 - Present
Undergraduate Student in Computer Science and Technology
Core Courses: Machine Learning, Modern Opertaing System, Computational Theory
📜 Publications

Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction
Boran Wen, Ye Lu, Keyan Wan, Sirui Wang, Jiahong Zhou, Junxuan Liang, Xinpeng Liu, Bang Xiao, Dingbang Huang, Ruiyang Liu, Yong-Lu Li*
Under review [Paper] | [Code] | [Project] | [Video]

ImDy: Human Inverse Dynamics from Imitated Observations
Xinpeng Liu, Junxuan Liang, Zili Lin, Haowen Hou, Yong-Lu Li*, Cewu Lu*
ICLR, 2025 [Paper] | [Code] | [Project] | [Video]

Homogeneous Dynamics Space for Heterogeneous Humans
Xinpeng Liu, Junxuan Liang, Chenshuo Zhang, Zixuan Cai, Cewu Lu*, Yong-Lu Li*
CVPR, 2025 [Paper] | [Code] | [Project] | [Video]

M$^3$-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation
Zixuan Chen, Jiaxin Li, Junxuan Liang, Liming Tan, Yejie Guo, Cewu Lu, Yong-Lu Li*
CVPR, 2025 [Paper] | [Project] | [Video]
📝 Project

Photovoltaic Power Generation Prediction System
Based on sparse coding, and distributed robust logistic regression algorithms
[Project]

LLM as a chatbot
SJTU CS4314 Natural Language Process final project
Finetune based on Qwen
[Project]

Machine Learning for 3D Bin Packing Problem
SJTU CS3308 Machine Learning final project
Based on behaviour cloning and RL
[Project]
💼 Research Experience
- Feb 2024 – Jan 2026: Research Intern
- RHOS team at Machine Vision and Intelligence Group (MVIG-RHOS), Shanghai Jiao Tong Univeisty, Shanghai, China
- Exploited the recently progressive human motion imitation algorithms and trained a data-driven human inverse dynamics solver in a fully supervised manner
- Supervised by Prof Yong-Lu Li and Prof Cewu Lu
- Sept 2023 – June 2024: Research Intern
- Department of Electrical Engineering, Shanghai Jiao Tong Univeisty, Shanghai, China
- Proposed a distributed photovoltaic state monitoring model based on sparse coding, and distributed robust logistic regression algorithms
- Supervised by Prof Xiaoyuan Xu
🥇 Awards🥈🥉🏅🎖️
- [2026] Outstanding Graduate of Shangha🥉, SJTU
- [2024] Merit Student (top 3%)🥇, SJTU
- [2024] National Special Award in Electronic&Electrical Engineering Innovation Competition🥇
- [2024] Meritorious Winner in Mathematical Contest In Modelling (Top 6.6%)🥉, America
🌐 related report
- [2024.08] 6项特等奖! 电院师生团队在第三届高校电气电子工程创新总决赛大放异彩
