Hung-Jui (Joe) Huang

I am a 5th-year Ph.D. student at CMU RI, co-advised by Prof. Michael Kaess and Prof. Wenzhen Yuan. My research focuses on superhuman tactile sensing and tactile-driven dexterous manipulation. On the tactile sensing side, I use touch to estimate physical properties, track object pose during contact, and create high-resolution 3D reconstructions.

I recently completed two research internships at Google DeepMind, working on multi-modal sensing for vision-language-action (VLA) models and real-world reinforcement learning, applied to dexterous and bimanual manipulation, where robots coordinate two hands for contact-rich tasks.

Before CMU, I received my B.Sc. in EECS from MIT and spent two years at ISEE working on self-driving trucks. I am a Presidential Fellow at CMU.

I am a 5th-year Ph.D. student at CMU RI, co-advised by Prof. Michael Kaess and Prof. Wenzhen Yuan. I am generally interested in robotics, computer vision, and machine learning. My research is about superhuman tactile sensing, including actively estimating physical properties, tracking object pose during contact, and creating high-resolution 3D reconstructions, as well as tactile-driven dexterous manipulation. I recently completed two research internships at Google DeepMind in London, working on multi-modal sensing for vision-language-action (VLA) models and real-world reinforcement learning. The work centered on bimanual manipulation, in which a two-armed robot or a humanoid with dexterous hands coordinates both arms to perform contact-rich tasks.

I received my B.Sc. in EECS at MIT. During my undergrad, I worked with Prof. Gregory Stein and Prof. Nicholas Roy. After B.Sc., I worked at ISEE for two years with Dr. Chris Baker and Prof. Ying Nian Wu. In the past, I have worked on robot navigation and self-driving trucks.

I am named a Presidential Fellow at CMU and my research is supported by the Paul and James Wang/Sercomm Presidential Scholarship.