Philadelphia, PA Email GitHub CV Résumé
Researching world models, robot learning, and embodied AI.
I am currently an M.S.E. student in Mechanical Engineering and Applied Mechanics at the University of Pennsylvania. My research interests lie in world models, robot learning, and robotic perception. I am broadly interested in learning predictive representations of the physical world and leveraging them for embodied intelligence and robot control.
University of PennsylvaniaM.S.E. in Mechanical Engineering and Applied MechanicsAccelerated Master’s Program with Shanghai Jiao Tong University (3+1+1)
Shanghai Jiao Tong UniversityB.S. in Mechanical Engineering
Open full-size figureUnified multimodal models can generate images and understand visual content, but forgetting a concept in one pathway does not necessarily remove it from the other. We introduce UUBench to evaluate cross-pathway concept unlearning and propose UniForget to jointly suppress target concepts while preserving other model capabilities.
Spring 2026
Calibrated stereo reconstruction and NeRF evaluation: 24.19 dB PSNR / 0.831 SSIM over six 100×100 test views in one scene.
Fall 2025
ESP32 master/slave sensing, Python gamepad control, wall following, Vive target navigation and timed competition-task sequences.
Fall 2025
Input-constrained MPC and clipped LQR on a nonlinear planar quadrotor, alongside minimum-snap waypoint planning.
Jun–Aug 2025
Collision-checked RRT paths, smooth joint timing and torque-driven tracking, checked against independent dynamics calculations.
Software Engineer Intern at UAES — United Automotive Electronic Systems Co., Ltd., Jun 2025 – Aug 2025.
Experience page →