Kai He

Kai He (何开)

I am a second-year PhD student at the University of Toronto, supervised by Prof. Igor Gilitschenski. I am current working as a research scientist intern at NVIDIA Toronto AI Lab.

Prior to my Ph.D. studies, I received my bachelor degree at ShanghaiTech University majoring in computer science and technology. I am fortunate to work with Prof. Jingyi Yu and Prof. Lan Xu during my undergraduate studies. I also spent an exciting summer in 2023 at Carnegie Mellon University as a research intern advised by Prof. Sebastian Scherer.

Email / CV / Google Scholar / Github / LinkedIn

Research

My research interests lie in generative models for 3D vision and graphics applications. My current research focuses on controllable generative video models for rendering, and further extends to physics-aware world modeling with real-time generation and interaction.

* Equal contribution ^† Joint advising

	ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler, Zian Wang, Huan Ling* Arxiv 2025 paper / arXiv
	LuxDiT: Lighting Estimation with Video Diffusion Transformer Ruofan Liang, Kai He, Zan Gojcic, Igor Gilitschenski, Sanja Fidler, Nandita Vijaykumar^†, Zian Wang^† NeurIPS 2025 paper / arXiv
	UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting Kai He, Ruofan Liang, Jacob Munkberg, Jon Hasselgren, Nandita Vijaykumar, Alexander Keller, Sanja Fidler, Igor Gilitschenski^†, Zan Gojcic^†, Zian Wang^† NeurIPS 2025 (Spotlight) paper / arXiv
	CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion Kai He, Chin-Hsuan Wu, Igor Gilitschenski CVPR 2025 paper / arXiv / code
	DressCode: Autoregressively Sewing and Generating Garments from Text Guidance Kai He, Kaixin Yao, Qixuan Zhang, Jingyi Yu^†, Lingjie Liu^†, Lan Xu^† SIGGRAPH 2024 (Journal Track, Best Paper Honorable Mention) paper / arXiv / code / dataset
	Relightable Neural Human Assets from Multi-view Gradient Illuminations Taotao Zhou, Kai He, Di Wu*, Teng Xu, Qixuan Zhang, Kuixiang Shao, Wenzheng Chen, Lan Xu, Jingyi Yu CVPR 2023 paper / arXiv / dataset
	Free-view Face Relighting using a Hybrid Parametric Neural Model on a SMALL-OLAT Dataset Youjia Wang, Kai He, Taotao Zhou, Kaixin Yao, Nianyi Li, Lan Xu, Jingyi Yu IJCV 2022 paper / code

Activities

Sept. 2024 ~ Dec. 2024: Teaching Assistant in CSC2545 Advanced Topics in ML: Geometric Deep Learning, University of Toronto

Sept. 2022 ~ Jan. 2023: Teaching Assistant in CS101 Algorithms and Data Structures, ShanghaiTech

Sept. 2020 ~ Jan. 2023: President and student coach of ACM Club, ShanghaiTech University

Sept. 2020 ~ Dec. 2022: Vice-President and core member of GeekPie, ShanghaiTech University

Selected Awards and Honors

2024: Best Paper Honorable Mention Award of ACM SIGGRAPH

2024: President's Award (top 2%), ShanghaiTech University

2024: Outstanding Graduates, Shanghai

2020, 2021: Merit Student, ShanghaiTech University

2021: Gold Medal, The 45th ICPC Asia Yinchuan Regional Contest

2020: Gold Medal, The 45th ICPC Asia Nanjing Regional Contest