Hang Gao
I am joining as a member of technical staff at
xAI , working on multimodal
and deep generative models.
Recently, I finished my PhD at UC Berkeley advised by
Angjoo Kanazawa . Before that, I studied at Jiao Tong University and
Columbia. I have also worked as a student researcher at
Stability, Adobe and Microsoft.
Research
toggle all
I am broadly interested in deep generative models for
world modeling. In the past, I have explored building
generalist systems that scale view synthesis to real-world
settings.
Your browser does not support the video tag.
Stable Virtual Camera: Generative View Synthesis with
Diffusion Models
Jensen (Jinghao) Zhou* , Hang Gao* ,
Vikram Voleti ,
Aaryaman Vasishta ,
Chun-Han Yao ,
Mark Boss ,
Philip Torr ,
Christrian Rupprecht ,
Varun Jampani
arXiv , 2025
project page
/
arXiv
/
code
/
demo
/
blog
We build a generalist multi-view diffusion model for view
synthesis in open, real-world settings.
Your browser does not support the video tag.
SOAR: Self-Occluded Avatar Recovery from a Single
Video
Zhuoyang Pan* ,
Angjoo Kanazawa ,
Hang Gao*
arXiv , 2024
project page
/
arXiv
/
code
We recover complete human avatars from self-occluded
videos in the wild.
Your browser does not support the video tag.
Shape of Motion: 4D Reconstruction from a Single
Video
Qianqian Wang* ,
Vickie Ye* , Hang Gao* ,
Jake Austin , Zhengqi Li ,
Angjoo Kanazawa
arXiv , 2024
project page
/
arXiv
/
code
We propose a method for joint 4D reconstruction and 3D
tracking on internet footages.
Your browser does not support the video tag.
NerfAcc: Efficient Sampling Accelerates
NeRFs
Ruilong Li ,
Hang Gao ,
Matthew Tancik ,
Angjoo Kanazawa
ICCV , 2023
project page
/
arXiv
/
code
We build and release a toolbox for accelerating all kinds
of NeRFs by efficient sampling.
Your browser does not support the video tag.
Monocular Dynamic View Synthesis: A Reality
Check
Hang Gao ,
Ruilong Li ,
Shubham Tulsiani ,
Bryan Russell ,
Angjoo Kanazawa
NeurIPS , 2022
project page
/
arXiv
/
video
/
code
We systematically show why and how existing 4D
reconstruction methods don't work well in the wild.
Long-term Human Motion Prediction with Scene
Context
Zhe Cao ,
Hang Gao ,
Karttikeya Mangalam ,
Qi-Zhi Cai , Minh Vo ,
Jitendra Malik
ECCV , 2020  
(Oral Presentation)
project page
/
arXiv
/
video
/
code
We predict long-term, diverse human motion in 3D by
understanding scene context from an image.
Deformable Kernels: Adapting Effective Receptive Fields
for Object Deformation
Hang Gao* ,
Xizhou Zhu* ,
Steve Lin ,
Jifeng Dai
ICLR , 2020
project page
/
arXiv
/
code
We propose a new convolutional operator that does
attention in the kernel space.
Spatio-Temporal Action Graph Networks
Roei Herzig* ,
Elad Levi* ,
Huijuan Xu* , Hang Gao , Eli Brosh,
Xiaolong Wang ,
Amir Globerson ,
Trevor Darrell
ICCV Workshop , 2019
arXiv
We find relational graph useful for action recognition.
Disentangling Propagation and Generation for Video
Prediction
Hang Gao* ,
Huazhe Xu ,
Qi-Zhi Cai ,
Ruth Wang , Fisher Yu ,
Trevor Darrell
ICCV , 2019
arXiv
We make a system that propagates seen parts and generates
unseen ones.
Low-shot Learning via Covariance-Preserving Adversarial
Augmentation Networks
Hang Gao ,
Zheng Shou ,
Alireza Zareian ,
Hanwang Zhang ,
Shih-Fu Chang
NeurIPS , 2018
arXiv
We learn feature augmentation for low-shot classifiers.
AutoLoc: Weakly-supervised Temporal Action Localization
in Untrimmed Videos
Zheng Shou ,
Hang Gao ,
Lei Zhang ,
Kazuyuki Miyazawa ,
Shih-Fu Chang
ECCV , 2018
arXiv
/
code
We propose a weakly-supervised method for temporal action
localization.
ER: Early Recognition of Inattentive Driving Events
Leveraging Audio Devices on Smartphones
Xiangyu Xu ,
Hang Gao ,
Jiadi Yu ,
Yingying Chen ,
Yanmin Zhu ,
Guangtao Xue ,
Minglu Li
INFOCOM , 2017
IEEE
We build an audio-based mobile app for inattentive driving
detection.
Thanks
Jon !
Last updated June 2025.