| CARVIEW |
Hi there!
I am a first-year CIS MSE student at the University of Pennsylvania. I am advised by Prof. Kostas Daniilidis at GRASP lab. My research interests lie in building systems that combine 3D computer vision and generative models to understand motion and enable intelligent, visually guided robots. Broadly, I’m excited about the intersection of 3D Vision, Graphics, and Embodied AI. I’m currently seeking Ph.D. positions and research internship opportunities in both academia and industry. If you think there’s a good match, feel free to reach out!
Previously, I was a research intern at the Geometric Computing Group at Stanford University under the supervision of Prof. Leonidas Guibas. I also spent a wonderful year visiting UC Berkeley, where I had the fortune to work with the Nerfstudio team at the BAIR Lab under the guidance of Prof. Angjoo Kanazawa. I did my undergraduate studies at ShanghaiTech University, where I was fortunate to be mentored by Prof. Jingyi Yu, Prof. Lan Xu, and Prof. Jiayuan Gu.
Outside of academics, my hobbies include playing the piano, photography, and drone flying. I’m also an avid traveler — so far, I’ve explored over 20 countries and regions across Africa, Asia, Australia, Europe, and North America.
- Computer Graphics
- Computer Vision
- Computational Photography
B.E. in Computer Science and Technology, 2025
ShanghaiTech University
Experience
Selected Projects
Under Review, 2025
We present Kirin, a comprehensive framework for learning and generating 3D quadruped motion directly from large-scale video data.
Under Review, 2025
We present a system to address the problem of reconstructing in-scene object manipulation from a monocular RGB video.
We present a new pipeline for dense animal pose annotation by optimizing general-purpose point trackers. Given a video and a few annotated frames, it fine-tunes a lightweight appearance embedding to adapt to the target animal, enabling accurate and automatic pose labeling across the entire video with minimal supervision.
JMLR MLOSS 2025
An open-source library for CUDA-accelerated differentiable rasterization of 3D gaussians with Python bindings. Mainly worked on python bindings, CUDA testing, and alpha-channel rendering.
