Zhixuan Liang

Zhixuan Liang 梁志烜

Ph.D Student

Department of Computer Science

The University of Hong Kong

liangzx@connect.hku.hk

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 & ACM Fellow).During 2024-2025, I was a visiting scholar at UC Berkeley MSC Lab, under the guidance of Prof. Masayoshi Tomizuka. I have interned at NVIDIA Research.

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. In 2020, I have been a research assistant at VIL of University of Washington, supervised by Prof. Chun Yuan.

Publications

	Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies Zhixuan Liang, Yizhuo Li, Tianshuo Yang, Chengyue Wu, Sitong Mao, Liuao Pei, Tian Nian, Shunbo Zhou, Xiaokang Yang, Jiangmiao Pang, Yao Mu, Ping Luo ICML, 2026
	Planning-aligned Token Compression for Long-Context Autonomous Driving Zhixuan Liang, Yuxiao Chen, Yurong You, Peter Karkus, Wenhao Ding, Boyi Li, Yan Wang, Alexander Popov, Maximilian Igl, Yiming Li, Danfei Xu, Nikolai Smolyanskiy, Boris Ivanovic, Ping Luo, Marco Pavone IEEE RA-L, 2026
	M²Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models Chunpu Xu, Zhixuan Liang^†, Yuhao Zhang, Chi-Min Chan, Jessie Wang, Yang Xiao, Mengkang Hu, Xiaokang Yang, Yao Mu^† ECCV, 2026
	ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs Xin Wu, Zhixuan Liang, Yue Ma^†, Mengkang Hu, Zhiyuan Qin, Xiu Li^† ACM MM, 2026
	DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation (Formerly: DexDiffuser: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation) Zhixuan Liang, Yao Mu, Yixiao Wang, Tianxing Chen, Wenqi Shao, Wei Zhan, Masayoshi Tomizuka, Ping Luo, Mingyu Ding CVPR, 2025
	G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation Tianxing Chen, Yao Mu, Zhixuan Liang, Zanxin Chen, Shijia Peng, Qiangyu Chen, Mingkun Xu, Ruizhen Hu, Hongyuan Zhang, Ping Luo CVPR, 2025*
	SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution Zhixuan Liang, Yao Mu, Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo CVPR, 2024
	AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners Zhixuan Liang, Yao Mu, Mingyu Ding, Fei Ni, Masayoshi Tomizuka, Ping Luo ICML, 2023 (Oral, Top 2.4%)
	Longitudinal Registration of Knee MRI Based on Femoral and Tibial Alignment Zhixuan Liang, Yin Guo, Chun Yuan ISMRM, 2021

Experiences

Research Intern, AV Group, NVIDIA Research, Santa Clara, CA, USA & Hong Kong SAR.
2025.08 - 2025.12
Supervised by: Dr. Yuxiao Chen, Dr. Boris Ivanovic and Prof. Marco Pavone.

Visiting Scholar, MSC Lab, University of California, Berkeley, California, CA, USA.
2024.06 - 2025.01
Topic: Planning with Diffusion Model.
Supervised by: Prof. Masayoshi Tomizuka (NAE Member).

Research Assistant, Vascular Imaging Lab, University of Washington, Seattle, WA, USA.
2020.06 - 2020.10
Topic: Multi-timepoint Registration of Knee MRI.
Supervised by: Dr. Yin Guo and Prof. Chun Yuan.