Yijia Weng

Yijia Weng | 翁伊嘉

I am a fifth-year Ph.D. student in computer science at Stanford University, advised by Prof. Leonidas Guibas. Previously, I obtained my B.S. in Computer Science from Turing Class, Peking University, advised by Prof. Baoquan Chen. I also had the privilege of working closely with Prof. Jeannette Bohg at Stanford, Prof. Hao Su at UCSD, and Prof. He Wang at Peking University. I've had a wonderful time pursuing research internships at Adobe Research, NVIDIA Research, and Google Deepmind.

Email / Google Scholar / Github

Research

My research interests lie in 3D computer vision, with a focus on reconstructing the 3D world with efficient, interaction-aware, and semantically meaningful representations.

	GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification Yijia Weng, Zhicheng Wang, Songyou Peng, Saining Xie, Howard Zhou, Leonidas Guibas Preprint, 2025 project page / arXiv
	MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds Jiahui Lei, Yijia Weng, Adam W. Harley, Leonidas Guibas, Kostas Daniilidis CVPR, 2025 project page / arXiv / code
	Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields Shijie Zhou, Hui Ren, Yijia Weng, Shuwang Zhang, Zhen Wang, Dejia Xu, Zhiwen Fan, Suya You, Zhangyang Wang, Leonidas Guibas, Achuta Kadambi CVPR, 2025 project page / arXiv / code
	Real2Code: Reconstruct Articulated Objects via Code Generation Mandi Zhao, Yijia Weng, Dominik Bauer, Shuran Song ICLR, 2025 project page / arXiv / code
	AO-Grasp: Articulated Object Grasp Generation Carlota Parés Morlans, Claire Chen, Yijia Weng, Michelle Yi, Yuying Huang, Nick Heppert, Linqi Zhou, Leonidas Guibas, Jeannette Bohg IROS, 2024 project page / arXiv / code
	Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects Yijia Weng, Bowen Wen, Jonathan Tremblay, Valts Blukis, Dieter Fox, Leonidas Guibas, Stan Birchfield CVPR, 2024 project page / arXiv / code
	Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks Yijia Weng, Kaichun Mo , Ruoxi Shi, Yanchao Yang, Leonidas Guibas ICML, 2023 project page / arXiv
	Leveraging SE(3) Equivariance for Self-supervised Category-Level Object Pose Estimation from Point Clouds Xiaolong Li, Yijia Weng, Li Yi, Leonidas Guibas, A. Lynn Abbott, Shuran Song, He Wang NeurIPS, 2021 project page / arXiv
	CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds Yijia Weng, He Wang, Qiang Zhou, Yuzhe Qin, Yueqi Duan, Qingnan Fan, Baoquan Chen, Hao Su, Leonidas Guibas ICCV, 2021 Oral Presentation project page / video / arXiv / code
	Unpaired Motion Style Transfer from Video to Animation Kfir Aberman, Yijia Weng, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen SIGGRAPH, 2020 project page / video / arXiv / code

Experience

	Stanford University, CA 2021.09 - Present Ph.D. Student in Computer Science Advisor: Prof. Leonidas Guibas
	Google Deepmind, CA 2024.07 - 2024.12 Student Researcher
	NVIDIA Research, WA 2023.06 - 2023.12 Research Intern
	Adobe Research, CA 2022.06 - 2022.09 Research Intern
	Peking University, China 2017.09 - 2021.07 B.S. in Computer Science, Turing Class Advisor: Prof. Baoquan Chen
	Stanford University, CA 2020.03 - 2020.11 Visiting Research Student through the UGVR program Advisor: Prof. Leonidas Guibas

Miscellaneous

I was quite into competitive programming💻 and used to compete in Olympiad in Informatics and International Collegiate Programming Contest (ICPC)🏅. Now I also train high school students back at home. Solving those brain teasers is always fun!
In my spare time, I enjoy dancing💃, cooking🍳, concerts🎫, musicals🎭, and learning foreign languages🇫🇷🇰🇷.

Template stolen from Jon Barron. Thanks for stopping by :)
Last updated: Oct 27, 2025