profile photo

Zhixuan Liang  梁志烜

Ph.D Student

Department of Computer Science

The University of Hong Kong

Email  /  CV  /  Google Scholar  /  Github

I am a Ph.D. student (2022-) of Computer Science at The University of Hong Kong, fortunately advised by Prof. Ping Luo and Prof. Wenping Wang (IEEE Fellow). During my PhD, I collaborate closely with Yao Mu (now at Shanghai AI Lab) and Dr. Mingyu Ding (now at UC Berkeley), working with Prof. Masayoshi Tomizuka.

Prior to that, I obtained my bachelor's degree with first place in Automation from Zhejiang University in 2021 and received an honor degree from Chu Kochen Honors College. I was a member of ACEE. In 2020, I have been a research assistant at VIL of University of Washington, supervised by Yin Guo and Prof. Chun Yuan.

I am currently looking for a visiting opportunity or summer intern position starting from Spring 2024. Please check my CV for details.


Publications
    My current research interests lie in generative model for planning, robot learning and embodied AI.
project image SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution
Zhixuan Liang, Yao Mu, Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Paper / Project page
project image RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation
Junting Chen, Yao Mu, Qiaojun Yu, Tianming Wei, Silang Wu, Zhecheng Yuan, Zhixuan Liang, Chao Yang, Kaipeng Zhang, Wenqi Shao, Yu Qiao, Huazhe Xu, Mingyu Ding, Ping Luo
(In Submission), 2024
Paper / Coming soon!
project image AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
Zhixuan Liang, Yao Mu, Mingyu Ding, Fei Ni, Masayoshi Tomizuka, Ping Luo
International Conference on Machine Learning (ICML), 2023   Oral Presentation (Top 2.4%)
Paper / Project page / Code
project image MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL
Fei Ni, Jianye Hao, Yao Mu, Yifu Yuan, Yan Zheng, Bin Wang, Zhixuan Liang
International Conference on Machine Learning (ICML), 2023
Paper / Project page
project image MeanAP-Guided Reinforced Active Learning for Object Detection
Zhixuan Liang, Xingyu Zeng, Rui Zhao, Ping Luo
(In Submission), 2023
Paper / Coming soon!
project image Longitudinal Registration of Knee MRI Based on Femoral and Tibial Alignment
Zhixuan Liang, Yin Guo, Chun Yuan
International Society for Magnetic Resonance in Medicine Annual Meeting (ISMRM), 2021
Paper / Code / Video

Experiences
Research Assistant, MMLAB, University of Hong Kong, Hong Kong SAR.
2022.09 - Present
Supervised by: Prof. Ping Luo and Prof. Wenping Wang.
Research Intern, Sensetime Research, Shanghai, China.
2021.06 - 2022.07
Topic: Active Learning for Object Detection.
Supervised by: Dr. Xingyu Zeng and Dr. Rui Zhao.
Research Assistant, Vascular Imaging Lab, University of Washington, Seattle, WA, USA.
2020.06 - 2020.10
Topic: Multi-timepoint Registration of Knee MRI.
Supervised by: Yin Guo and Prof. Chun Yuan.

Selected Honors and Awards
  • Hong Kong PhD Fellowship Scheme (HKPFS), 2022-2026
  • HKU Presidential PhD Scholarship (HKU-PS), 2022-2026
  • Y S and Christabel Lung Postgraduate Scholarship, 2022
  • National Scholarship, 2020
  • Wang Guosong Dean’s Award, Zhejiang University, 2021
  • Outstanding Graduate of Zhejiang Province, 2021
  • Finalist Award in Mathematical Contest in Modeling, 2020
  • First Prize in Mathematics Competition of Chinese College Students, 2020

Teaching
  • COMP3278: Introduction to Database Management System, HKU, Fall 2023
  • DASC7606: Deep Learning, HKU, Spring 2023

© Zhixuan Liang | Last updated: February 2024