(Cannon Beach, Oregon)
Google scholar
/ GitHub
/ Blog
/ LinkedIn
I am a research scientist at Horizon Robotics. Previously, I worked at Baidu Research and Facebook AI Research.
My early research involved various topics such as object segmentation, language grounding in video, video captioning , embodied language understanding, and the lottery ticket hypothesis. Since joining Horizon Robotics in 2019, I've been researching novel RL algorithms (hierarchical RL, safe/constrained RL, and exploration, etc) and building learning-based real-world robots.
Over the course of my career, as the first author I have published papers in top conferences such as ACL, CVPR, NeurIPS, ICLR, CoRL, CVPR, and AAAI, covering a wide range of topics including deep RL, robotics, language grounding, embodied AI, multimodal learning, image/video segmentation, etc. I strongly believe that achieving AGI requires the integration of diverse disciplines. My endeavors have been recognized with distinction, particularly marked by the receipt of the Best Paper Award at ACL 2013 for my work on grounded language learning from video.
I am also an experienced engineer who loves writing code and building things. I am a co-author and an active maintainer of ALF, an RL framework emphasizing on the flexibility and easiness of implementing a complex RL system involving many different algorithm components.
My current passion is to combine all my past experience on multimodal learning and learning-based robotic control to build an agile robot, with mobile manipulation capabilities, that follows natural language commands in daily indoor scenarios.
Ph.D. of Electrical and Computer Engineering (ECE), Purdue University |
Bachelor of Computer Science (CS), Peking University |
ALF - Agent Learning Framework
(ALF) is a PyTorch reinforcement learning framework emphasizing on the flexibility
and easiness of implementing complex algorithms involving many different
components.
TAAC - Temporally abstract actor-critic
algorithm for efficient continuous control.
XWorld - A simulator
package for RL research with language task support.
FLARE - A reinforcement learning framework for
training embodied agents with PyTorch.
I like playing video games, especially ARPG. So far my favorite games are souls-like, by FromSoftware.