My research focuses on building Heterogeneous Physical Intelligence for robots by composing specialized models across modalities and time scales.
Multisensory Learning: Integrating vision, touch, audio, and language for fine-grained and effective manipulation.
Structured Action Representations: Learning compositional action abstractions from diverse data including simulation, teleoperation, human video, and off-policy data.
Predictive Manipulation: Learning physics-inspired world models for contact-rich robotic manipulation.
I'm always excited to explore new collaborations in robotics and machine learning! If you're interested, please drop me an email. I'd love to chat!
haonan_chen [at] seas (dot) harvard (dot) edu /
haonan [at] cs (dot) stanford (dot) edu CV /
Google Scholar /
Twitter
News
To junior PhD/master/undergraduate students: If you'd like to chat about life, career plans, or research ideas in ML/robotics, please feel free to email me to schedule a meeting. I dedicate 30 minutes each week for these conversations and encourage students from underrepresented groups or anyone in need to reach out.
OAT: Ordered Action Tokenization
Chaoqi Liu,
Xiaoshen Han,
Jiawei Gao,
Yue Zhao,
Haonan Chen,
Yilun Du Preprint 2026, [Project][Paper][Code][Blog][BibTeX] Media Coverage:[MarkTechPost]@misc{liu2026orderedactiontokenization,
title={OAT: Ordered Action Tokenization},
author={Chaoqi Liu and Xiaoshen Han and Jiawei Gao and Yue Zhao and Haonan Chen and Yilun Du},
year={2026},
eprint={2602.04215},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2602.04215},
}
IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation
Jiawei Gao,
Chaoqi Liu,
Peilin Wu,
Haonan Chen,
Yilun Du Preprint 2026, [Project][Paper][Code][Video][BibTeX]@article{gao2024impact,
title={Learning Internal-Model Predictive Control for Forceful Robotic Manipulation},
author={Gao, Jiawei and Liu, Chaoqi and Wu, Peilin and Chen, Haonan and Du, Yilun},
journal={arXiv preprint arXiv:2406.14558},
year={2024}
}
SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models
Haowen Liu*,
Shaoxiong Yao*,
Haonan Chen,
Jiawei Gao,
Jiayuan Mao,
Jia-Bin Huang,
Yilun Du * Equal contribution CVPR 2026, [Project][Paper][BibTeX]@article{simpact2025,
title={SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models},
author={Liu, Haowen and Yao, Shaoxiong and Chen, Haonan and Gao, Jiawei and Mao, Jiayuan and Huang, Jia-Bin and Du, Yilun},
journal={arXiv preprint arXiv:2512.05955},
year={2025}
}