Jiaying Fang

I'm a first-year Robotics PhD student at Cornell University, co-advised by Professors Hadas Kress-Gazit and Preston Culbertson. My current research focuses on making robotic policies safe, reliable, and interpretable.

Previously, I worked with Professor Tapomayukh Bhattacharjee at Cornell on physical human-robot interaction. I received my MS in EE from Stanford University where I was fortunate to have worked with Professor Jeannette Bohg on learning robot policies from human videos; and Professor Allison Okamura on force aware robot policies. In summer 2024, I interned at Intuitive Surgical. Prior to that, I received my BEng (Hons) in EIE from Hong Kong Polytechnic University.

Email  /  Scholar  /  Twitter  /  Linkedin

Publications

We propose E2-CARE, a framework that enables context-aware adaptation by representing primitive caregiving skills as interaction templates whose execution is reshaped online.

We propose Engagement-aware MPC (E-MPC), a user-engagement-aware method that plans interaction to maintain engagement while respecting a workload constraint.

We introduce a method that edits in-the-wild egocentric human videos to bridge the visual embodiment gap between humans and robots and then learns a robot policy with these edited videos.

A framework for modular policies that combines module-level uncertainty with models of human intervention cost to decide when and which module to query, evaluated on synthetic experiments and a robot-assisted bite acquisition system.

We present a scalable framework for training manipulation policies directly from human video demonstrations, requiring no robot data.

We study imitation-learning policies for autonomous tissue retraction on the dVRK that use tool-tissue forces alongside vision and kinematics, and show they are more successful and gentler than policies trained without force.

Teaching

CS5750: Foundations of Robotics Graduate Teaching Assistant, Cornell University, Fall 2025