About me

I am an incoming Ph.D. student in Electrical and Computer Engineering at Purdue University, advised by Prof. Ziran Wang. Before that, I received my M.S. in Computer Science from Columbia University and my B.Eng. from Zhejiang University.

My research interests broadly lie in machine learning and its intersections with autonomous systems and computer vision. I am especially interested in building interpretable and generalizable learning-based systems that support effective, robust, safe, and trustworthy autonomy.

I’m always happy to chat about research, collaborations, or shared interests — feel free to reach out via email! 🤝✨

News

[Aug 2026] I am excited to begin my Ph.D. journey at Purdue ECE. Boiler Up! 🚂🎓🌟

[Jan 2026] Our paper on uncertainty-aware robot navigation was accepted to ACC 2026 🎉

Projects

Gaussian Mixture-Based Inverse Perception Contract for Uncertainty-Aware Robot Navigation

American Control Conference(ACC), 2026, [paper], [code]

This project models perception uncertainty for safe navigation by representing uncertainty as multiple Gaussians, the approach captures fine-grained structures that baseline method overlook. This enables more effective motion planning while maintaining probabilistic safety guarantees.

Tactile-based Online Active Shape Exploration and Reconstruction using Reinforcement Learning

Project available on GitHub, 2025, [code]

This is a team project of Deep Learning for Robotic Manipulation course at Columbia. It learns an RL policy for active 3D shape exploration using tactile sensing, enabling robots to perceive objects that are visually occluded. The system is built and evaluated in IsaacSim/IsaacLab with diverse geometries, demonstrating effective online tactile-based reconstruction of unseen objects.

Region Attentioned Text-guided 3D Deformation

Project available on GitHub, 2024, [code]

This is a team project from the Deep Learning for Computer Vision course at Columbia. We improved a SOTA text-guided shape editing framework ChangeIt3D by leveraging a region-attended editor that leverages shape correspondence to enable more precise, localized geometry modifications.

Teaching

COMS 4995 – Deep Learning for Computer Vision, TA, Fall 2025, Columbia University