Justin (Zhaocong) Yuan

ML Research @ Qualcomm | ex-Nvidia | ex-Apple | MASc UofT

profile.png

I obtained my MASc degree in RL and Robotics from University of Toronto, advised by Angela Schoellig at Dynamic Systems Lab (DSL), also part of Vector Institute and UofT Robotics Institute. Previously, I received my BASc degree in Engineering Science from UofT. I was also an intern in Nvidia Toronto AI lab advised by Sanja Fidler, Apple Siri team based in Seattle, and Data-Driven Decision Making Lab advised by Scott Sanner. My prior works largely focus on safe RL, transfer learning, and Sim-to-Real tasks.

I currently work at Qualcomm to develop multi-modal Transformer models for mobile/on-device applications, exploring various topics such as model distillation, quantization, and parameter efficient finetuning for LLMs or other foundation models.

In my leisure time, I play fingerstyle guitar :guitar: and badminton :badminton:.

news

Sep 25, 2024 Paper “Stepping Forward on the Last Mile” accepted to NeurIPS 2024. [link] :sparkles: :smile:
Feb 21, 2023 Join Qualcomm as a Machine Learning Research Engineer on the Embedded AI (eAI) Team.
Oct 23, 2022 IROS 2022 presentation of our safe-control-gym paper.

latest posts

selected publications

  1. IROS
    safe-Control-Gym: A Unified Benchmark Suite for Safe Learning-Based Control and Reinforcement Learning in Robotics
    IEEE Robotics and Automation Letters, 2022
  2. Annual Reviews
    Safe learning in robotics: From learning-based control to safe reinforcement learning
    Annual Review of Control, Robotics, and Autonomous Systems, 2022
  3. ICCV
    Meta-sim: Learning to generate synthetic datasets
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019