Publications: NeurIPS 2025, AAWR: Real-World Reinforcement Learning of Interactive Perception Behaviors; CoRL 2025, RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies (Oral Presentation); Blog: Evaluating pi0 in the Wild: Strengths, Problems, and the Future of Generalist Robot Policies; Awards: ZeroMimic wins best paper in CVPR2025 3DVLMs workshop!
Research Experience
Fall 2025 - Present, Graduate Research Assistant, Daniilidis Research Group, GRASP Lab, Advisor: Prof. Kostas Daniilidis, Improving spatial reasoning of VLAs like Pi05 via reinforcement learning; Summer 2025, Research Intern, Dyna Robotics, Advisor: Jason Ma && York Yang, Building an embodied reasoning VLA for fine-grained manipulation tasks; Fall 2024 - Present, Graduate Research Assistant, PennPAL Research Group, GRASP Lab, Advisor: Prof. Dinesh Jayaraman, Building VLMs-based Manipulation System via Diffusion Policy for fine-grained tasks; Summer 2024, Multimodal MLE Intern, IDEA-Computer Vision & Robotics Department, Advisor: Dr. Xiaoke Jiang & Prof. Lei Zhang, Built, trained, and optimized a small human-centric video captioning model based on Grounding DINO 1.6Pro.
Education
2024—Present, University of Pennsylvania, M.S.E. in Robotics, Advisor: Prof. Dinesh Jayaraman; 2020—2024, Zhejiang University, B.E. in Electronic and Computer Engineering; 2020—2024, University of Illinois at Urbana-Champaign, B.S. in Computer Engineering, Advisor: Prof. Said Mikki, Thesis: Intelligent Pour-Over Coffee Machine.
Background
Research interests include VLAs, embodied reasoning, and robot learning. Passionate about building generalizable agents capable of fine-grained manipulation, such as making a cup of latte with an espresso machine.
Miscellany
Other activities include representing MSROBO at CIS Department Meeting, joining GRASP Student, Faculty and Industry (SFI) Committee Meeting, and participating in various academic events.