Published several papers, including 'From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models' (co-first author), 'VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model' (co-first author), and 'CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos'.
Research Experience
During his Master’s, he worked with Prof. Chen Feng on scene representation for robotics and Dr. Yubei Chen on unsupervised representation learning. Currently, interning at Samsung Research America, Mountain View, guided by Dr. Luowei Zhou.
Education
Earned a Bachelor's degree in Electrical Engineering from Tsinghua University (2016-2020), followed by a Master's degree in Computer Science from NYU (2021-2023). Since 2023, pursuing a Ph.D. in Computer Science at NYU under the supervision of Professor Chen Feng.
Background
Currently a second-year PhD student in Computer Science at the Courant Institute of New York University, with research interests focusing on learning scene representations that are useful for robots to understand and interact with the world.
Miscellany
The name 'Juexiao' comes from a famous poem in the Tang Dynasty, depicting a quiet spring morning.