Han Qi's Homepage

Publications

Han Qi*, Yi Su*, Aviral Kumar*, Sergey Levine. Data-Driven Offline Decision-Making via Invariant Representation Learning. (A.k.a. Data-Driven Offline Model-Based Optimization via Invariant Representation Learning.) NeurIPS, 2022.

Han Qi*, Frederic Wang*, Alfredo De Goyeneche, Michael Lustig, Efrat Shimron. K-band: A self-supervised strategy for training deep-learning MRI reconstruction networks using only limited-resolution data. ISMRM 2023 (Oral presentation).

Han Qi, Stefano Rando, Xinyang Geng, Iku Ohama, Aviral Kumar, Sergey Levine. Latent Conservative Objective Models for Offline Data-Driven Crystal Structure Prediction. ICLR 2023 ML4Materials workshop.

Xuezhi Du*, Han Qi*, Wenbin Ji, Peiyuan Li, Run Hua, Wenliang Hu, Feng Qi. Construction of a Colorectal Cancer Prognostic Risk Model and Screening of Prognostic Risk Genes Using Machine-Learning Algorithms. Comput Math Methods Med, 2022; Oct 11. doi: 10.1155/2022/9408839, eCollection.

(*Co-first authors)

Research

Deep Reinforcement Learning Research

Robotics and AI Lab (RAIL) - UC Berkeley, advised by Prof. Sergey Levine

*Apply representation layer to solve distributional shift problem for offline optimization problem.
*Collaboration with Panasonic for optimizing molecule structure for lower energy.

MR Image Reconstruction Research

MikLab - UC Berkeley, advised by Prof. Michael Lustig

*Develop training methods for MRI reconstruction without access to full-area ground truth information.

Bioinformatics Research

Tianjin Medical University (Tianjin, China)

*Find out the relationship between genes and survival time for CRC patients via machine learning.

UUV semi-automatic design project

Berkeley AI Research (BAIR) - UC Berkeley, advised by Prof. Sanjit Seshia and Prof. Sebastian Junges

*Predict future patterns for UUV motion with simulation data to realize goal of semi-automatically design.

Image Processing Research

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

*Changing the ratio of an image intelligently according to its contents: an image processing tool based on pixel weight and face detection.

Others

Teaching Experience

*Tutor for CS61A (The Structure and Interpretation of Computer Programs) - Fall 2020, Spring 2021
*Reader for EECS126 (Probability and Random Processes) - Spring 2021
*Teaching Assistant for EECS126 (Probability and Random Processes) - Fall 2021
*Teaching Assistant for CS186 (Introduction to Database Systems) - Fall 2022

About Me

I am a Ph.D. student from Harvard, advised by Prof. Heng Yang. Previously I did my undergraduate study in UC Berkeley majoring in computer science. My research interest is about robust machine learning and computer vision.