Tianyuan (Roger) Dai

I'm a first-year PhD student at UT Austin, advised by Prof. Yuke Zhu. I am also a research intern at NVIDIA Generalist Embodied Agent Research (GEAR) group. My research is at the intersection of robotics, machine learning, and computer vision. I am especially passionate about developing generalizable robot skills.

Previously, I obtained my MS in Computer Science at Stanford University, where I investigated real-to-sim-to-real and sim-to-real paradigms for robot manipulation, advised by Prof. Li Fei-Fei at Stanford Vision and Learning Lab and Stanford PAIR Group. I obtained BS in Computer Science and Mathematics at HKUST, where I worked on 3D vision, advised by Prof. Chi-Keung Tang and Prof. Yu-Wing Tai.

I am open to collaboration and enjoy chatting with people from different research areas. Feel free to drop me an email.

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 currently studying how to achieve generalizable robot manipulation skills in a user and data-efficient manner, from both algorithm and data perspectives.

News

• [2025.08] Join RPL as a PhD student.

• [2025.06] Start summer internship at NVIDIA GEAR Lab.

• [2025.06] ROSETTA released.

• [2024.10] ACDC released.

• [2024.09] ACDC accepted to CoRL 2024.

Publications

* Equal Contribution

Teaching

Website Template