ZiTian Chen (陈梓天)
I am a solopreneur wearing every hat: researcher, engineer, and operator.
I earned my Ph.D. from UMass Amherst (advised by Prof. Erik Learned-Miller) and hold a Bachelor's degree from Fudan University. My expertise lies in computer vision and game theory.
Industry experience (AI): RoboForce, IBM-MIT, Google DeepMind, and NVIDIA Research.
Solo experience (Game Theory): built systems to crush online wagering platforms.
Since 2026, I have gone all in on Physical AI, architecting and leading the end-to-end development of high-precision robotic systems. I drive the full technical stack—from data strategy and model training to precision control and closed-loop execution—with an uncompromising focus on accuracy and reliability.
Selected Publications
-
Toward Unified Expertise: Learning a Single Model from Diverse Perception
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Zitian Chen, Mingyu Ding, Yikang Shen, Erik Learned-Miller, and Chuang Gan
-
LegoNet: Dynamic Structured Optimization via Mixture-of-Experts
Zitian Chen, Mingyu Ding, Yikang Shen, Wei Zhan, Erik Learned-Miller, Chuang Gan
-
Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners
CVPR 2023
Zitian Chen, Yikang Shen, Mingyu Ding, Zhenfang Chen, Hengshuang Zhao, Erik Learned-Miller, Chuang Gan
-
Image Deformation Meta-network for One-shot Learning
Best paper finalist and Oral at CVPR 2019
Zitian Chen, Yanwei Fu, Yu-Xiong Wang, Lin Ma, Wei Liu, Martial Hebert
-
Shot in the Dark: Few-Shot Learning with No Base-Class Labels
Learning from Limited and Imperfect Data workshop at CVPR 2021
Zitian Chen, Subhransu Maji, Erik Learned-Miller
-
Cross-Supervised Object Detection
Arxiv
Zitian Chen, Zhiqiang Shen, Jiahui Yu, Erik Learned-Miller
-
Multi-level Semantic Feature Augmentation for One-shot Learning
IEEE Transactions on Image Processing(TIP)
Zitian Chen, Yanwei Fu, Yinda Zhang, Leonid Sigal
-
Image Block Augmentation for One-Shot Learning
AAAI 2019
Zitian Chen, Yanwei Fu, Kaiyu Chen, Yu-Gang Jiang
