Zhuoyang Pan
Seeking research internships

Zhuoyang Pan

Incoming CIS PhD Student, University of Pennsylvania

Advised by Prof. Kostas Daniilidis at the GRASP Lab

I build 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 research internship opportunities — if you think there's a good match, feel free to reach out.

Previously, I was a research intern at Stanford University, working with Prof. Leonidas Guibas, Dr. Adam W. Harley, and Prof. Shangzhe Wu. I also spent a year at UC Berkeley with the Nerfstudio team at BAIR, under Prof. Angjoo Kanazawa. I received my undergraduate degree from ShanghaiTech University.

Outside of research, I play the piano, shoot photography, and fly drones. I'm also an avid traveler — so far I've explored over 20 countries and regions across five continents.

Research Interests

Robotics Computer Graphics Computer Vision

Education

Ph.D. & M.S. in Computer & Information Science
University of Pennsylvania
Aug 2025 — Present
B.E. in Computer Science & Technology
ShanghaiTech University
2021 — 2025
01

Experience

Research Assistant
Aug 2025 — Present
Philadelphia, PA
Research Intern
Jun 2024 — Dec 2024
Stanford, CA
Visiting Student, Computer Science
Aug 2023 — May 2024
Berkeley, CA
Bachelor Student, Computer Science & Technology
Sep 2021 — Jun 2025
Shanghai, China
02

Selected Projects

Kirin

Kirin: Animal Motion Generation from In-the-wild Video

Brian Nlong Zhao*, Zhuoyang Pan*, James Matthew Rehg, Jiajun Wu, Shangzhe Wu

Under Review · 2025

A comprehensive framework for learning and generating 3D quadruped motion directly from large-scale video data.

Reisom

Reisom: Zero-shot Reconstruction of In-Scene Object Manipulation

Dixuan Lin, Tianyou Wang, Zhuoyang Pan, Yufu Wang, Lingjie Liu, Kostas Daniilidis

Under Review · 2025

A system for reconstructing in-scene object manipulation from a single monocular RGB video.

PosePAL

PosePAL: Efficient Animal Pose Labeling Using Point Trackers

Zhuoyang Pan, Boxiao Pan, Guandao Yang, Adam W. Harley, Leonidas Guibas

CV4Animals @ CVPR 2025 · Oral · Invited to IJCV

A pipeline for dense animal pose annotation by optimizing general-purpose point trackers — fine-tuning a lightweight appearance embedding from a few annotated frames to label an entire video with minimal supervision.

SOAR

SOAR: Self-Occluded Avatar Recovery from a Single Video

Zhuoyang Pan*, Angjoo Kanazawa, Hang Gao*

arXiv · 2024

Recovering human avatars from self-occluded internet videos where people show only parts or sides of their body.

Gsplat

gsplat: An Open-Source Library for Gaussian Splatting

Vickie Ye*, Ruilong Li*, Justin Kerr, Matias Turkulainen, Brent Yi, Zhuoyang Pan, Otto Seiskari, Jianbo Ye, Jeffrey Hu, Matthew Tancik, Angjoo Kanazawa

JMLR MLOSS · 2025

An open-source library for CUDA-accelerated differentiable rasterization of 3D Gaussians with Python bindings. I worked on the Python bindings, CUDA testing, and alpha-channel rendering.

Nerfstudio

Nerfstudio

Nerfstudio Team · BAIR, UC Berkeley

Open-Source Framework

A modular framework for neural radiance field development. I worked mainly on the integration of Gaussian splatting.