Jialei Chen

Zhongguancun Academy

Beijing, China

s-cjl@bza.edu.cn

I am Jialei Chen (陈佳磊), a Ph.D. student at Zhongguancun Academy. I work closely with Prof. Chao Yu at Zhongguancun Academy on embodied intelligence, and I am also advised by Prof. Yuanbo Xu at Jilin University. My research focuses on embodied intelligence, especially learning from human egocentric videos and latent dynamics for robot agents. My goal is to build data-efficient embodied agents that learn from human experience, understand physical dynamics, and generalize to real-world tasks.

Before moving into embodied intelligence, my published work explored generative models, time-series modeling, and data mining. You can find my publication record on Google Scholar. Code and research projects are available on GitHub.

Please feel free to contact me at s-cjl@bza.edu.cn for research discussion or collaboration.

news

Aug 01, 2026	I joined Striding.AI as a research intern to lead a pretraining project. I am excited to see what we can build together.
Aug 01, 2026	We gave three talks on LaWAM, focusing on latent dynamics modeling and latent action models for efficient robot learning. Watch a talk video here. (3D视觉工坊, 青稞AI, 具身智能之心)
Jun 23, 2026	We released the LaWAM code and published a detailed blog post describing the method, experiments, and real-robot results.
Jun 14, 2026	We released our new paper LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies (arXiv).
Jun 01, 2026	Academic homepage initialized with al-folio.

selected publications

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

Jialei Chen, Kai Wang, Kang Chen, and 9 more authors

arXiv, 2026

arXiv Bib HTML Talk Blog Code

@article{chen2026lawam,
  title = {LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies},
  author = {Chen, Jialei and Wang, Kai and Chen, Kang and Chen, Shuaihang and Gao, Feng and Tang, Wenhao and Li, Zhiyuan and Liu, Weilin and Yao, Zhuyu and Li, Boxun and Xu, Yuanbo and Yu, Chao},
  journal = {arXiv},
  year = {2026},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
  preview_video = {hero_libero_object_grid.mp4},
  talk = {https://www.bilibili.com/video/BV12D3g6ME3b?t=10.5}
}

Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach

Jialei Chen, Yuanbo Xu, and Yiheng Jiang

In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025

DOI arXiv Bib HTML Code

@inproceedings{chen2025unlocking,
  title = {Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach},
  author = {Chen, Jialei and Xu, Yuanbo and Jiang, Yiheng},
  booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  pages = {155--166},
  year = {2025},
  publisher = {ACM},
  doi = {10.1145/3711896.3737172},
}

Deep Generative Imputation Model for Missing Not at Random Data

Jialei Chen, Yuanbo Xu, Pengyang Wang, and 1 more author

In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

DOI arXiv Bib HTML

@inproceedings{chen2023deep,
  title = {Deep Generative Imputation Model for Missing Not at Random Data},
  author = {Chen, Jialei and Xu, Yuanbo and Wang, Pengyang and Yang, Yongjian},
  booktitle = {Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},
  pages = {316--325},
  year = {2023},
  publisher = {ACM},
  doi = {10.1145/3583780.3614835},
}