Tianyuan (Roger) Dai

I'm a Master's student in Computer Science at Stanford University, affiliated with the Stanford Vision and Learning Lab and Stanford PAIR Group. I have the privilege of conducting cutting-edge research in embodied AI and robotic learning, advised by Prof. Fei-Fei Li. Previously, I obtained a Bachelor's degree in Computer Science and Mathematics at the Hong Kong University of Science and Technology (HKUST), where I worked on 3D and multimodal generation, advised by Prof. Chi-Keung Tang and Prof. Yu-Wing Tai.

Special thanks to Prof. Hao Su, whose talk at HKUST in my final undergraduate semester inspired me to transition from computer vision to embodied AI. I am also deeply grateful to Josiah Wong, Yunfan Jiang, Chen Wang, and Ruohan Zhang for their invaluable advice on my research projects at Stanford.

I am looking for a PhD position starting from 2025 fall.

Email  /  Scholar  /  LinkedIn

Research

My long-term vision is to integrate human-level understanding of real-world environments into robotics algorithms that assist people with daily tasks using data-driven approaches. I am passionate about both designing reliable robotic systems and developing innovative algorithms that enable more robust policies, ultimately paving the way for intelligent household robots. Recently, my focus has been on developing real-to-sim-to-real paradigms for robust manipulation policy learning.

News

• [2024.10] ACDC released.

• [2024.09] ACDC accepted to CoRL 2024.

Publications

* Equal Contribution

Teaching

Website Template