Mingjie Zhou

Mingjie Zhou 「周明杰」

I am a third-year undergraduate student at Fudan University, majoring in Microelectronics. Currently, I am a research intern at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, advised by Prof. Yang Gao. I am also an intern at Sharpa Robotics.

Previously, I had the pleasure of working with Prof. Yao Mu at Shanghai AI Lab and SCALE Lab, Shanghai Jiao Tong University, and with Prof. Fan Yang at the State Key Lab of Integrated Circuits and Systems, Fudan University.

Email / CV / Github

Research

My goal is to build generalist robots that can learn by interacting with the physical world. I am now interested in robot learning, dextrous manipulation, robotic foundation models and reinforcement learning. I am also interested in world model and continual learning. Previously, I also worked on LLM for analog circuit design automation.

Authors marked with ∗ contributed equally. Authors marked with † are corresponding authors.

	FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation Chengbo Yuan, Zicheng Zhang, Mingjie Zhou, Wendi Chen, Yi Wang, Zhuoyang Liu, Dantong Niu, Shuo Wang, Hui Zhang, Wenkang Zhang, Yingdong Hu, Yuanqing Gong, Wanli Xing, Chuan Wen, Cewu Lu, Kaifeng Zhang†, Yang Gao† In Submission, 2026.* project page / arXiv / code / model / dataset FTP-1 is the first generalist foundation tactile policy, pretrained on ~3,000 hours from 26 sources and 21 tactile sensors to transfer contact-rich manipulation skills across heterogeneous sensors and embodiments, including +31.6% gains on unseen sensor setups.
	SynManDex: Synthesizing Human-like Dexterous Grasps from Synthetic Human Pre-Grasps Yanming Shao, Zanxin Chen, Wenwei Lin, Mingjie Zhou, Tianxing Chen, Xiaokang Yang, Yichen Chi†, Yao Mu† In Submission, 2026. project page / paper / arXiv / resources SynManDex uses synthetic human pre-grasps as affordance-aware proposals, then retargets, force-closure optimizes, and validates robot-native rollouts to build human-like dexterous manipulation demonstrations.
	AnalogSeeker: An Open-source Foundation Language Model for Analog Circuit Design Zihao Chen, Ji Zhuang, Jinyi Shen, Xiaoyue Ke, Xinyi Yang, Mingjie Zhou, Zhuoyao Du, Xu Yan, Zhouyang Wu, Zhenyu Xu, Jiangli Huang, Li Shang, Xuan Zeng, Fan Yang† ACM Transactions on Design Automation of Electronic Systems (TODAES), 2026. An open-source foundation language model for analog circuit design.

Research Experiences

	Vision and Robotics Lab, Tsinghua University Dec. 2025 - Present Research Intern, advised by Prof. Yang Gao. Research on tactile-driven robotic foundation models and large-scale multimodal manipulation datasets.
	SCALE Lab, Shanghai Jiao Tong University Sep. 2025 - Dec. 2025 Research Intern, advised by Prof. Yao Mu. Research on human-like dexterous grasping data generation and evaluation.
	State Key Lab of Integrated Circuits and Systems, Fudan University Feb. 2025 - Sep. 2025 Research Intern, advised by Prof. Fan Yang. Research on LLM reinforcement learning for analog circuit design automation.

Industrial Experiences

Sharpa Robotics
Dec. 2025 - Present
Robotic Algorithm Intern. Working on building Vision-Tactile-Language-Action(VTLA) model for dexterous manipulation.

Honors

• National Scholarship, 2024-2025

• National Scholarship, 2022-2023

• Shanghai Government Scholarship, 2023-2024

• Second Prize, 9th National University Student Integrated Circuit Innovation Competition, 2025

• Second Prize, Contemporary Undergraduate Mathematical Contest in Modeling, Shanghai Division, 2025

• Second Prize, Mathematics Competition of Chinese College Students, Shanghai Division, 2024

• Second Prize, Chinese Physics Olympiad, Zhejiang Province, 2021