Zeju Li

Email: zeju (dot) li (dot) cs [at] gmail (dot) com

I'm an undergraduate student at Zhejiang University, pursuing a bachelor's degree in Computer Science and Technology (expected to graduate in Jun 2027).

Fascinated by movies such as I, Robot, Real Steel, and Big Hero 6, I am passionate about developing truly intelligent robots capable of general-purpose autonomy in human-centric environments.

I am currently a research intern at MLL-Lab, Northwestern University, where I am fortunate enough to be advised by Prof. Manling Li and Prof. Ruohan Zhang. Previously, I had the privilege of working as a research assistant at the State Key Lab of CAD&CG, Zhejiang University, under the guidance of Prof. Hao Chen and Prof. Chunhua Shen.

I am seeking Ph.D. opportunities for Fall 2027 and would be glad to connect about research and potential collaborations.

Google Scholar CV (Oct 2026) GitHub
LinkedIn Twitter

News

Sep 5, 2026 STAIR is accepted to CoRL-2026! 🎉

Mar 31, 2026 AGILE is accepted to SIGGRAPH-2026!

Feb 21, 2026 StaMo is accepted to CVPR-2026 as an Highlight Presentation!

Nov 08, 2025 ODYSSEY is accepted to AAAI-2026 as an Oral Presentation!

Research

* Equal contributions, † Corresponding author

	LAGEN: Are Vision-Language Agents Latency Aware? Talha Chafekar^, Zihan Wang^, Zeju Li^, Xinyuan Li^, Qineng Wang, Jiajun Wu, Yuke Zhu, Yi Dong, Zhiding Yu, Ruohan Zhang, Manling Li ^* Author order is interchangeable. [project page] [paper] Preprint, 2026 Profiling deployment latency and training vision-language-action agents for real-time control.
	Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments Mingyu Liu^, Zeju Li^, Jiuhe Shu, Hanqing Wang, Yuhao Chao, Hao Chen^†, Chunhua Shen^† [project page] [arXiv] CoRL, 2026 Robust robot learning needs corrective alignment dynamics, not just fluent expert trajectories.
	StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation Mingyu Liu^, Jiuhe Shu^, Hui Chen, Zeju Li, Canyu Zhao, Jiange Yang, Shenyuan Gao, Hao Chen^†, Chunhua Shen^† [project page] [arXiv] CVPR, 2026 [Highlight Presentation, Top 3.1%] Compact state representations for efficient world modeling and action learning.
	ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks Kaijun Wang^, Liqin Lu^, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu^†, Hao Chen^†, Chunhua Shen^† [project page] [arXiv] AAAI, 2026 [Oral Presentation, Top 3.5%] Language-guided long-horizon mobile manipulation with a benchmark.
	AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation Jin-Chuan Shi^, Binhong Ye^, Tao Liu, Junzhe He, Yangjinhui Xu, Xiaoyang Liu, Zeju Li, Hao Chen^†, Chunhua Shen^† [project page] [arXiv] SIGGRAPH, 2026 [Conference Track] Reconstruct simulation-ready hand-object interaction from monocular video via agentic generation and robust pose tracking.