Jing-Chen Peng
Jing-Chen Peng is a Ph.D. student in robotics at the Georgia Institute of Technology, where he is affiliated with the School of Electrical and Computer Engineering. He is a co-first author of GT-VLA, a framework that translates high-level vision-language model guidance into visual traces to steer low-level vision-language-action model execution for robotic manipulation. He previously earned an M.S. in Computer Science from the University of Illinois at Urbana-Champaign, where he contributed to the AVATRINA humanoid teleoperated robot and research on vision-based tactile sensing.
“translates high-level VLM guidance into visual traces to steer low-level VLA execution on unseen tasks and configurations”
Source→“Jing-Chen Peng... Co-first author, equal contribution. Co-designed the trace-conditioned action learning and data augmentation strategies.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.