|
Josh Tran
I'm Josh, a MS student at the University of Washington. I am currently researching RL and IL for robotic manipulation at the WEIRD Lab under
Prof. Abhishek Gupta. During undergrad, I enjoyed two years working on state estimation for Flying
Insect Robots (FIRs) at the AIR Lab under Prof. Sawyer Fuller.
I have also had the good fortune of working as software engineering intern first at Github in 2024, and then at Amazon Robotics in 2025. I am graduating in Spring 2027, and am open to roles in ML and robotics.
Email /
Scholar /
Twitter /
Github /
LinkedIn
|
|
Research
I'm interested in reinforcement learning and continual learning.
|
|
|
OmniReset: Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning
Patrick Yin*,
Tyler Westenbroek*,
Zhengyu Zhang,
Joshua Tran,
Ignacio Dagnino,
Eeshani Shilamkar,
Numfor Mbiziwo-Tiapo,
Simran Bagaria,
Xinlei Liu,
Galen Mullins,
Andrey Kolobov,
Abhishek Gupta
(* indicates equal contribution)
ICLR 2026
project page
/
arXiv
We leverage large-scale RL and diverse resets to solve dexterous, contact-rich manipulation tasks with no reward engineering or demos. We distill to RGB and show zero-shot sim2real transfer.
|
|
|
TinySense: A Lighter Weight and More Power-efficient Avionics System for Flying Insect-scale Robots
Zhitao Yu*,
Josh Tran*,
Claire Li, Aaron Weber, Yash P. Talwekar, Sawyer Fuller
(* indicates equal contribution)
ICRA 2025
Best Student Paper Award
project page
/
arXiv
Created the smallest viable avionics suite and first light and efficient enough for Flying Insect Robots (FIRs).
|
|