Zhuoyang Liu

Zhuoyang Liu | 刘卓洋

Hi there! I'm a third-year undergraduate student at Peking University, majoring in Computer Science. Currently, I am a visiting student at BAIR at UC Berkeley, advised by Prof. Trevor Darrell. Prior to this, I was a research intern at the HMI Lab at Peking University, advised by Prof. Shanghang Zhang. My research interests lie in the application of multimodal large models, specifically VLA models, in robot manipulation.

Email / Scholar / Twitter / Github / WeChat

News

[2026.06] I am awarded the SenseTime Scholarship 2026! (30 recipients nationwide)
[2026.04] One paper (LaST₀) is accepted to ICML 2026 as a spotlight (top 2.2%)!
[2026.02] One paper (ManualVLA) is accepted to CVPR 2026!
[2026.01] One paper (MLA) is accepted to ICRA 2026!
[2026.01] One paper (HybridVLA) is accepted to ICLR 2026!
[2025.09] Two papers (Fast-in-Slow, AC-DiT) are accepted to NeurIPS 2025!
[2025.08] One paper (3DS-VLA) is accepted to CoRL 2025!

Selected Publications

I'm interested in Computer Vision, Robot Learning and Embodied Large Multimodal Models. My research focuses on how to enhance large multimodal models to better reason about the physical world and develop effective task planning. Some papers are highlighted.

	T-Rex: Tactile-Reactive Dexterous Manipulation Dantong Niu^, Zhuoyang Liu^, Zekai Wang^, Boning Shao, Zhao-Heng Yin, Anirudh Pai, Yuvan Sharma, Stefano Saravalle, Ruijie Zheng, Jing Wang, Ryan Punamiya, Mengda Xu, Yuqi Xie, Yunfan Jiang, Letian Fu, Konstantinos Kallidromitis, Matteo Gioia, Junyi Zhang, Jiaxin Ge, Haiwen Feng, Fabio Galasso, Wei Zhan, David M. Chan, Yutong Bai, Roei Herzig, Jiahui Lei, Fei-Fei Li, Ken Goldberg, Jitendra Malik, Pieter Abbeel, Yuke Zhu, Danfei Xu, Jim (Linxi) Fan, Trevor Darrell arXiv*, 2026 project page / arXiv / code / dataset T-Rex introduces a large-scale tactile dataset of 100 hours and a variable-rate Mix-of-Transformer (MoT) architecture with a temporal tactile VQ-VAE encoder, achieving ~30% higher success rates across 12 real-world tasks involving force control and deformable object handling.
	LaST₀: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model Zhuoyang Liu^, Jiaming Liu^, Hao Chen^, Jiale Yu, Ziyu Guo, Chengkai Hou, Chenyang Gu, Xiangju Mi, Renrui Zhang, Kun Wu, Zhengping Che, Jian Tang, Pheng-Ann Heng, Shanghang Zhang ICML*, 2026 (spotlight, top 2.2%) project page / arXiv / code A VLA model that enables efficient reasoning before acting through a Latent Spatio-Temporal Chain-of-Thought (CoT), capturing fine-grained physical and robotic dynamics that are often difficult to verbalize.
	ManualVLA: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation Chenyang Gu^, Jiaming Liu^, Hao Chen^, Runzhong Huang^, Qingpo Wuwu, Zhuoyang Liu, Xiaoqi Li, Ying Li, Renrui Zhang, Peng Jia, Pheng-Ann Heng, Shanghang Zhang CVPR, 2026 project page / arXiv / video A unified VLA framework built upon a Mixture-of-Transformers (MoT) architecture, enabling coherent collaboration between multimodal manual generation and action execution.
	DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action Zhen Fang^, Zhuoyang Liu^, Jiaming Liu, Hao Chen, Yu Zeng, Shiting Huang, Zehui Chen, Lin Chen, Shanghang Zhang, Feng Zhao arXiv, 2025 project page / arXiv DualVLA improves action performance through carefully designed post-training while preserving the reasoning ability.
	MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulation Zhuoyang Liu^, Jiaming Liu^, Jiadong Xu, Nuowei Han, Chenyang Gu, Hao Chen, Kaichen Zhou, Renrui Zhang, Kai Chin Hsieh, Kun Wu, Zhengping Che, Jian Tang, Shanghang Zhang ICRA, 2026 project page / arXiv / code A multisensory language-action (MLA) model that collaboratively perceives heterogeneous sensory modalities and predicts future multisensory objectives to facilitate physical world modeling.
	AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation Sixiang Chen^, Jiaming Liu^, Siyuan Qian^, Han Jiang, Xiaoqi Li, Renrui Zhang, Zhuoyang Liu, Chenyang Gu, Chengkai Hou, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang NeurIPS*, 2025 project page / arXiv / code Adaptive Coordination Diffusion Transformer (AC-DiT) enhances mobile base and manipulator coordination for end-to-end mobile manipulation.
	Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning Hao Chen^, Jiaming Liu^, Chenyang Gu^, Zhuoyang Liu^, Renrui Zhang, Xiaoqi Li, Xiao He, Yandong Guo, Chi-Wing FU, Shanghang Zhang, Pheng-Ann Heng NeurIPS, 2025 project page / arXiv / code Unlike previous dual-system VLA methods that attach a separate policy head as System 1, FiS-VLA repurposes the final transformer blocks of an intact VLM as System 1, while retaining the full model for System 2 reasoning.
	HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model Jiaming Liu^, Hao Chen^, Zhuoyang Liu^, Pengju An^, Renrui Zhang, Chenyang Gu, Xiaoqi Li, Ziyu Guo, Sixiang Chen, Mengzhen Liu, Chengkai Hou, Mengdi Zhao, Kaichen Zhou, Pheng-Ann Heng, Shanghang Zhang ICLR, 2026 project page / arXiv / code HybridVLA innovatively integrates diffusion and autoregressive action prediction within a single LLM, fully leveraging the continuity and probabilistic nature of diffusion alongside the reasoning capabilities of autoregressive modeling.

Education

	University of California, Berkeley Visiting Student, Berkeley Global Access (BGA) Program 2026.01 - Present
	Peking University B.S. in Computer Science, Yuanpei College 2023.08 - Present

Research Experience

	UC Berkeley Research Intern, Berkeley AI Research 2026.01 - Present Research on Embodied AI and Robot Manipulation Research Advisor: Prof. Trevor Darrell
	Simplexity Robotics Research Intern 2025.09 - 2026.01 Research on Embodied AI and Robot Manipulation
	Beijing Innovation Center of Humanoid Robotics Research Intern 2025.08 - 2026.01 Research on Embodied AI and Robot Manipulation
	AI2Robotics Research Intern, X-Lab 2025.06 - 2026.01 Focused on Vision-Language-Action (VLA) models
	Peking University Research Intern, HMI (Human Machine Intelligence) Lab 2024.07 - Present Embodied AI Research Advisor: Prof. Shanghang Zhang

Honors & Awards

2026	SenseTime Scholarship 2026 (only 30 recipients in China)
2025	Academic Rising Star Award Nomination (Undergraduate Program), Peking University
2025	Third Prize in the first round of the RoboTwin Dual-Arm Collaboration Challenge, CVPR 2025
2024	Top 16 in the Mahjong AI Competition Finals, IJCAI 2024
2023	Qin-Jin Scholarship, Peking University
2022	Gold Medalist, 36th Chinese Chemistry Olympiad; Member of the National Training Squad (Top 50 Nationwide)

This homepage is designed based on Jon Barron's website and deployed on Github Pages.