Han Qi

Ph.D. Candidate in Computer Science, Harvard SEAS

Email: hqi (at) g.harvard.edu

Biography

I am a second-year Ph.D. student in the School of Engineering and Applied Sciences (SEAS) at Harvard University. I am advised by Prof. Heng Yang in the Computational Robotics Lab. Previously, I received my Bachelar degree from UC Berkeley in Computer Science with Highest Distinction in General Scholarship, where I had the fortune to work with Prof. Sergey Levine in the RAIL lab at BAIR.

I am interested in designing robot learning algorithms that can robustly generalize and rapidly adapt in new environments, and understanding the robot learning pipelines behind.

Research

(* indicates equal contribution)

Control-Oriented Clustering of Visual Latent Representation

Han Qi^*, Haocheng Yin^*, and Heng Yang

Preprint
Homepage / Paper / Code (Coming soon) / bibtex

@article{qi2024control,
  title={Control-oriented Clustering of Visual Latent Representation},
  author={Qi, Han and Yin, Haocheng and Yang, Heng},
  journal={arXiv preprint arXiv:2410.05063},
  year={2024}
}

Closure: Fast quantification of pose uncertainty sets

Yihuai Gao^*, Yukai Tang^*, Han Qi, and Heng Yang

RSS 2024
Paper / bibtex

@article{gao2024closure,
  title={CLOSURE: Fast Quantification of Pose Uncertainty Sets},
  author={Gao, Yihuai and Tang, Yukai and Qi, Han and Yang, Heng},
  journal={arXiv preprint arXiv:2403.09990},
  year={2024}
}

Latent conservative objective models for offline data-driven crystal structure prediction

Han Qi^*, Xinyang Geng^*, Stefano Rando, Iku Ohama, Aviral Kumar, and Sergey Levine

ICLR 2023 ML4Materials workshop, 2023
Paper / bibtex

@article{qi2023latent,
  title={Latent Conservative Objective Models for Data-Driven Crystal Structure Prediction},
  author={Qi, Han and Geng, Xinyang and Rando, Stefano and Ohama, Iku and Kumar, Aviral and Levine, Sergey},
  journal={arXiv preprint arXiv:2310.10056},
  year={2023}
}

K-band: Self-supervised MRI Reconstruction via Stochastic Gradient Descent over K-space Subsets

Frederic Wang^*, Han Qi^*, Alfredo De Goyeneche, Reinhard Heckel, Michael Lustig, and Efrat Shimron

ISMRM 2023 (Oral)
Paper / Code / bibtex

@inproceedings{wang2023kband,
  title={{K-band: Training self-supervised reconstruction networks using limited-resolution data}},
 author={F. Wang and Qi, Han and De Goyeneche, Alfredo, and Lustig, Michael and E. Shimron},
 booktitle={Proceedings of the ISMRM Workshop on Data Sampling and Imaging Reconstruction, Sedona},
 year={2023.}
},
@inproceedings{qi2023kband,
  title={{K-band: Training self-supervised reconstruction networks using limited-resolution data}},
 author={H. Qi and Wang, F. and  De Goyeneche, Alfredo, and Lustig, Michael and E. Shimron},
 booktitle={Proceedings of the ISMRM Annual Meeting, Toronto},
 year={2023.}
},

Data-Driven Offline Decision-Making via Invariant Representation Learning

Han Qi^*, Yi Su^*, Aviral Kumar^*, and Sergey Levine

NeurIPS 2022
Paper / Code / bibtex

@article{qi2022data,
  title={Data-driven offline decision-making via invariant representation learning},
  author={Qi, Han and Su, Yi and Kumar, Aviral and Levine, Sergey},
  journal={Advances in Neural Information Processing Systems},
  volume={35},
  pages={13226--13237},
  year={2022}
}

Changing the Ratio of an Image Intelligently According to its Contents: An Image Processing Tool Based on Pixel Weight and Face Detection

Han Qi

Winning third prize from AAAI in 2018 ISEF (International Science and Engineering Fair), one of the largest international pre-college science competitions
Paper / Poster