Hong-Xing "Koven" Yu

Ph.D. Candidate

Computer Science Department

Stanford University

Email: koven@cs.stanford.edu

Google Scholar / Github / Twitter

Current Research Topics

Physical Scene Understanding
Dynamics Models and Simulation
3D/4D Visual Generation

I am a PhD candidate at the Stanford Vision and Learning Lab in the Computer Science department of Stanford University, advised by Jiajun Wu. My research centers around how AI can understand, generate, and interact with the physical world. I spent two wonderful summers at Google Research, working with Noah Snavely and Bill Freeman. Prior to Stanford, I visited UC San Diego to work with Manmohan Chandraker.

Publications (Show selected / Show all by date / Show all by topic)

Current Research Topics: Physical Scene Understanding / Dynamics Models and Simulation / 3D/4D Visual Generation; Past Research Topic: Person Re-Identification

(* indicates equal contributions)

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions [Teaser]

Zizhang Li*, Hong-Xing Yu*, Wei Liu, Yin Yang, Charles Herrmann, Gordon Wetzstein, Jiajun Wu

ICCV 2025 / Paper / Website

WorldScore: A Unified Evaluation Benchmark for World Generation [Teaser]

Haoyi Duan*, Hong-Xing Yu*, Sirui Chen, Li Fei-Fei, Jiajun Wu

ICCV 2025 / Paper / Website / Leaderboard

WonderWorld: Interactive 3D Scene Generation from a Single Image [Teaser]

Hong-Xing Yu*, Haoyi Duan*, Charles Herrmann, William T. Freeman, Jiajun Wu

CVPR 2025 / Paper / Website

Highlight

FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video [Teaser]

Yue Gao*, Hong-Xing Yu*, Bo Zhu, Jiajun Wu

CVPR 2025 / Paper / Website

Oral Presentation

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation [Teaser]

Tianyuan Zhang, Hong-Xing Yu, Rundi Wu, Brandon Y. Feng, Changxi Zheng, Noah Snavely, Jiajun Wu, William T. Freeman

ECCV 2024 / Paper / Website

Oral Presentation

WonderJourney: Going from Anywhere to Everywhere [Teaser]

Hong-Xing Yu, Haoyi Duan, Junhwa Hur, Kyle Sargent, Michael Rubinstein, William T. Freeman, Forrester Cole, Deqing Sun, Noah Snavely, Jiajun Wu, Charles Herrmann

CVPR 2024 / Paper / Website

Fluid Simulation on Neural Flow Maps [Teaser]

Yitong Deng, Hong-Xing Yu, Diyang Zhang, Jiajun Wu, Bo Zhu

ToG (SIGGRAPH Asia 2023) / Paper / Website

Best Paper Award

Inferring Hybrid Neural Fluid Fields from Videos [Teaser]

Hong-Xing Yu*, Yang Zheng*, Yuan Gao, Yitong Deng, Bo Zhu, Jiajun Wu

NeurIPS 2023 / Paper / Website

Unsupervised Discovery of Object Radiance Fields [Teaser]

Hong-Xing Yu, Leonidas J. Guibas, Jiajun Wu

ICLR 2022 / Paper / Website