Hao Zhang

Hao Zhang 张昊

Ph.D. Candidate, University of Illinois Urbana-Champaign · Research Scientist Intern, World Labs

I work on world models, 3D/4D reconstruction and generation, animation and rigging, and differentiable physical simulation. Always open to research collaborations, academic discussions, and mentoring.

Email Google Scholar GitHub X CV 小红书 WeChatzh17603602632
Atlas: A World Model for Spatial Intelligence
World Labs, 2026  ·  I co-led Atlas 3D with Bardienus Duisterhof — reconstruction and explicit 3D outputs

News

Recent updates
Sep 1, 2026

World Labs released Atlas, a world model for spatial intelligence. I co-led Atlas 3D with Bardienus Duisterhof.New

Jul 19, 2026

FreeOrbit4D accepted by SIGGRAPH 2026.

Jul 13, 2026

RegHead (ECCV 2026) is out — project page, paper, code, and dataset.

Jun 12, 2026

World Tracing (first author) is out — paper, project page, code, and live demo are available.

Feb 20, 2026

RigMo (first author) accepted by CVPR 2026; code and data will be released soon.

Nov 14, 2025

Joining World Labs in San Francisco as a Research Scientist Intern from January 2026.

Sep 18, 2025

SP4D (first author) accepted by NeurIPS 2025 as a Spotlight.

Jun 25, 2025

PhysRig (first author) accepted by ICCV 2025.

Jun 2, 2025

Joined Snap Research (New York) as a Research Scientist Intern.

May 27, 2025

One paper (first author) accepted by TMLR 2025.

Feb 17, 2025

Selected as a Meshy Fellowship 2025 Finalist.

Sep 16, 2024

Joined Stability AI.

May 2, 2024

Joined Pixocial AI Lab in Seattle.

May 2, 2024

One paper (first author) accepted by ICML 2024.

Jan 16, 2024

One paper (first author) accepted by ICLR 2024.

Dec 8, 2023

One paper (first author) accepted by AAAI 2024.

Oct 24, 2023

One paper (first author) accepted by WACV 2024.

Publications

Selected · * equal contribution
World Tracing
arXiv 2026

World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible

Hao Zhang1,2, Mohamed El Banani1, Jen-Hao Cheng1, Paul Zhang1, Yi Hua1, Ben Mildenhall1, Christoph Lassner1, Narendra Ahuja2, Gengshan Yang1

1World Labs  ·  2University of Illinois Urbana-Champaign

RegHead
ECCV 2026

RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration

Jiahao Luo1, Hao Zhang2, Jianqi Chen3, Yijie He4, Jiaxu Zou4, Michael Vasilkovsky4, Sergei Korolev4, Sergey Tulyakov4, Chaoyang Wang4, Peter Wonka3, James Davis1, Jian Wang4

1UC Santa Cruz  ·  2UIUC  ·  3KAUST  ·  4Snap Inc.

FreeOrbit4D
SIGGRAPH 2026

FreeOrbit4D: Training-free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction

Wei Cao1, Hao Zhang1, Fengrui Tian2, Yulun Wu1, Yingying Li1, Shenlong Wang1, Ning Yu3,4, Yaoyao Liu1

1University of Illinois Urbana-Champaign  ·  2University of Pennsylvania  ·  3Eyeline Labs  ·  4Netflix

RigMo
CVPR 2026

RigMo: Unifying Rig and Motion Learning for Generative Animation

Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou

Stable Part Diffusion 4D
NeurIPS 2025 · Spotlight

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation

Hao Zhang, Chun-Han Yao, Simon Donné, Narendra Ahuja, Varun Jampani

RGB-Only
NeurIPS 2025 · Spotlight

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

Fang Li, Hao Zhang, Narendra Ahuja

PhysRig
ICCV 2025

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework

Hao Zhang*, Haolan Xu*, Chun Feng, Varun Jampani, Narendra Ahuja

MagicPose4D
TMLR 2025

MagicPose4D: Crafting Articulated Models with Appearance and Motion Control

Hao Zhang*, Di Chang*, Fang Li, Mohammad Soleymani, Narendra Ahuja

S3O
ICML 2024

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton

Hao Zhang, Fang Li, Samyak Rawlekar, Narendra Ahuja

LIMR
ICLR 2024

LIMR: Learning Implicit Representation for Reconstructing Articulated Objects

Hao Zhang, Fang Li, Samyak Rawlekar, Narendra Ahuja

CSL
AAAI 2024

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation

Hao Zhang, Fang Li, Lu Qi, Ming-Hsuan Yang, Narendra Ahuja

Open-NeRF
WACV 2024

Open-NeRF: Towards Open Vocabulary NeRF Decomposition

Hao Zhang, Fang Li, Narendra Ahuja

Experience & Education

Experience
World Labs
Research Scientist Intern · 2026 Jan – Present
Snap Research
Research Scientist Intern · 2025 Summer – 2025 Dec
Stability AI
Research Scientist Intern · 2024 Fall – 2025 Summer
Pixocial AI Lab
Research Scientist Intern · 2024 Summer
Shanghai AI Lab
Research Intern · 2021.10 – 2022.06
Education
University of Illinois Urbana-Champaign
Ph.D. in Computer Vision · 2022 – 2027 (expected)
University of Southern California
M.S. in Electrical & Computer Engineering · 2019 – 2020
CUHK, Shenzhen
Visiting Student · 2021.03 – 2021.10
Civil Aviation University of China
B.S. in Telecommunication Engineering · 2014 – 2018

Academic Service

Reviewing
Conferences

ICLR · NeurIPS · ICML · CVPR · ICCV · ECCV · AAAI

Journals

IEEE TPAMI · IEEE TIP

Beloved Companions

Fifi and Taotao

Fifi

Born 2022-08-14  ·  6 lbs  · 

Taotao

Born 2025-02-14  ·  4 lbs  ·