Zichen "Charles" Zhang
charlesz at allenai dot org
I am Predoctoral Young Investigators (PYI) on the PRIOR team at AI2 supervised by Luca Weihs. Previously, I was also fortunate to collaborate with people from Stanford Vision & Learning Lab (SVL) and NVIDIA, supervised by Jim Fan and Yuke Zhu. I graduated from Macalester College in Dec. 2022 advised by Prof. Andrew Beveridge and Susan Fox.
The Generalist can specialize, and the Specialist can generalize.
I am interested in both generalist and specialist agents, with a focus on developing generalizable and effective approaches that can be applied across a wide range of tasks and scenarios.
09/2023: Release Universal Visual Decomposer: Long-Horizon Manipulation Made Easy, an off-the-shelf method immediately enables RL from vision without reward engineering and compositional generalizations in IL for long-horizon manipulation tasks in sim and real, without any extra training, task knowledge, and costs.
04/2023: Release When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learning, towards only request intervention (reset) when necessary, while nailing generalizations
12/2022: Join PRIOR @ AI2 as Predoctoral Young Investigator (PYI)
10/2022: Release VIMA, a single agent can solve visual goal, one-shot video imitation, novel concept grounding, visual constraint, etc.
(* indicates equal contribution, †
indicates equal advising)
Conference/Workshop Reviewer: ICRA 2024, CVPR 2024, NeurIPS 2023, CoRL 2023
04/2023: "Autonomous Visuomotor Reinforcement Learning" at Ranjay Krishna group.
Teaching Assistant at Macalester College
09/2022: Comp 484 Intro to Artificial Intelligence
01/2022: MATH 378 Complex Analysis
09/2021: STAT/COMP 112 Intro to Data Science
01/2021: COMP 394 Topics Course: Reinforcement Learning
(design and write code implementations for homework and class materials)
09/2020: COMP 128 Data Structure
01/2020: STAT/COMP 112 Intro to Data Science