Zekun Hao

Email: zhao (at) nvidia [dot] com

About

I am a Research Scientist at NVIDIA Deep Imagination Research. I work on Generative AI and the development of Cosmos world foundation models. My research spans 3D generation, Vision-Language Models (VLMs), and video synthesis.

I received my Ph.D. in Computer Science from Cornell University, where I was advised by Prof. Serge Belongie and supported by the 2022-2023 NVIDIA Graduate Fellowship. Prior to joining NVIDIA full-time, I interned at Adobe (2019) and NVIDIA (2020-2023).

Selected Publications

Refer to the Google Scholar page for the up-to-date list.

World Simulation with Video Foundation Models for Physical AI
Arxiv 2025
NVIDIA
[Paper] [Website] [Code] [BibTex]
Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale
Arxiv 2024
Zekun Hao*, David W. Romero*, Tsung-Yi Lin, Ming-Yu Liu.
[Paper] [Website] [Blog] [Youtube] [BibTex]
Implicit Neural Representations with Levels-of-Experts
NeurIPS 2022
Zekun Hao, Arun Mallya, Serge Belongie, Ming-Yu Liu.
[Paper] [Paper+supp] [Poster] [BibTex]
GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds
ICCV 2021 (Oral)
Zekun Hao, Arun Mallya, Serge Belongie, Ming-Yu Liu.
[Paper] [Code] [Website] [Video] [BibTex]
Learning Gradient Fields for Shape Generation
ECCV 2020 (Spotlight)
Ruojin Cai*, Guandao Yang*, Hadar Averbuch-Elor, Zekun Hao, Serge Belongie, Noah Snavely, Bharath Hariharan.
[Paper] [Code] [Website] [BibTex]
DualSDF: Semantic Shape Manipulation using a Two-Level Representation
CVPR 2020
Zekun Hao, Hadar Averbuch-Elor, Noah Snavely, Serge Belongie.
[Paper] [Code] [Website] [CVPR Daily Coverage] [Demo1] [Demo2] [BibTex]
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
ICCV 2019 (Oral)
Guandao Yang*, Xun Huang*, Zekun Hao, Ming-Yu Liu, Serge Belongie, Bharath Hariharan.
[Paper] [Code] [Website] [Video] [BibTex]
Controllable Video Generation with Sparse Trajectories
CVPR 2018
Zekun Hao, Xun Huang, Serge Belongie.
[Paper] [Code] [BibTex]

Last update: 01/19/2026