Ran (Thomas) Tian - 田然
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 am also a Qualcomm Innovation Fellow , a World Artificial Intelligence Conference Rising Star , a Robotics: Science and Systems Pioneer, and a Microsoft Future Leaders in Robotics and AI .

My research lies in the intersection of robotics and AI with a focus on safe alignment between embodied agents and humans. I tackle the alignment and safety problems that emerge throughout the life-cycle of foundation models in robotics, ranging from: training (wherein we need to collect and quantify what kinds of embodied data will enable the desired robotics capabilities), to fine-tuning (wherein we must align these models with humans), to deployment (where these models must run in real-time, reliably detect out-of-distribution scenarios, and confidently handover control to fallback-strategies). 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.

During my PhD study, I am a long-term intern at Waymo (2022-Now), working on foundational motion model for autonomous driving research (including pre-training, post-training preference alignment, and distillation for onboard deployment). I am fortunate to have the opportunity to intern at the Autonomous Vehicle Research Group at NVIDIA Research, working on visual foundational models for autonomous driving (2023-2024). Previously, I was a research intern at WeRide, Honda Research Institute, and Qualcomm AI Research.

I am actively looking for an industrial RS or a postdoctoral position! Please reach out to me if you think I might be a good fit!

google scholar   |   twitter   

• 

  [Feb 2025]

  Our paper with Waymo on efficient post-training preference alignment for motion generation is accepted by ICLR as a

  spotlight (notable top 5%)

  .
• 

  [Jan 2025]

  We are running the Safely Leveraging VLMs in Robotics Worksop at ICRA.
• 

  [Jan 2025]

  One new arXiv paper: VLM-in-the-loop policy steering!

• [Sep 2024]

  Three papers accepted by CoRL! One on using VLM to handle long-tail events in autonomous driving, one on system-level failure detection for motion prediction model refinement, and one on MoE policies for robot manipulation.

• [Jun 2024]

  I was named a Rising Star and won the Yunfan Award at the World Artificial Intelligence Conference this year (top 15 early career Chinese AI researchers)!

• [May 2024]

  I was named a Robotics: Science and Systems Pioneer this year (top 30 early career researchers around the world in the robotics field)!

• [Apr 2024]

  I won the 2024 Qualcomm Innovation Fellowship (32 winners in North America)!

• [Mar 2024]

  I won the finalist award in the Baidu AI Fellowship this year (top 20 Phd students in the AI field around the world)!

• [Mar 2024]

  Our work RT-X won the 2024 Finalists for ICRA Best Paper, Best Student Paper, and Best Manipulation Paper Awards

• [Mar 2024]

  Check out our new preprint on a general calibrated regret metric for detecting and mitigating system-level human-robot interaction failures and how it can be used to identify informative deployment data for efficiently improving behavior prediction models.

• [Jan 2024]

  Our work on visual representation alignment for robot learning was accepted to ICLR 2024! We propose a tractable video-only method for solving the visual representation alignment problem and learning visual robot rewards. Check out the new results in the arXiv version.

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

* indicates equal contribution and co-authorship.

website adapted from here