Ran (Thomas) Tian
rantian [at] berkeley [dot] edu

I am a PhD student at UC Berkeley advised by Prof. Masayoshi Tomizuka and Prof. Andrea Bajcsy at Carnegie Mellon University. I spent Summer 2023 at Waymo working on large autoregressive model for autonomous vehicle motion generation and efficient deployment. I also spent Summer 2022 at Waymo working on learning autonomous vehicle behavior scoring function from human feedback. Previously, I was a research intern at WeRide, Honda Research Institute, and Qualcomm AI Research.

My research lies in the intersection of robotics and AI with a focus on alignment between embodied agents and humans. I am interested in enabling embodied agents to act in accordance with human intentions and in close proximity to humans because they understand human preferences and the safety implications that can arise from misaligned models. I ground my work through a variety of applications, from autonomous cars, to personalized robots, to generative AI and in experiments with real human participants.

google scholar   |  

• [Nov 2023]

  Check out our new preprint in which we propose a tractable video-only method for solving the visual representation alignment problem and learning visual robot rewards!

• [Nov 2023]

  I will be starting an internship at NVIDIA Research!

• [Oct 2023]

  Together with Google Brain, DeepMind, and 34 labs around the world, we released our dataset for large scale robot learning!

• [May 2023]

  I will be starting an internship at Waymo!

• [Jan 2023]

  Our paper on modeling & influencing the dynamics of human learning was accepted to HRI 2023!

For the most up-to-date list of publications, please see google scholar.

* indicates equal contribution and co-authorship.

(Honorable Mention for Best Paper)

(Best Paper Nomination)

website adapted from here