Xun Huang Profile Photo

Xun Huang

Senior Research Scientist, Adobe Research
Adjunct Faculty, CMU
Pittsburgh, PA

Email: xuhuang at adobe dot com

Google Scholar | Twitter/X | GitHub | Selected Publications | Teaching

My name is Xun Huang (pronounced as /shuun hwang/). I am a Senior Research Scientist at Adobe and also an Adjunct Faculty at CMU. My recent research focuses on real-time, interactive, and autoregressive video/world models. I lead the interactive video world model research at Adobe.


I was a researcher at NVIDIA prior to joining Adobe. I developed one of the first text-to-image demo with multimodal control (GauGAN2), coauthored papers that serve as the basis of NVIDIA's text-to-image and text-to-3D foundation models and shipped them into production.


I obtained my PhD in Computer Science from Cornell in 2020, advised by Professor Serge Belongie. During my PhD, I invented Adaptive Instance Normalization (AdaIN) and was the first to demonstrate its effectiveness in generative neural networks. AdaIN became a foundational component of StyleGAN and played a key role in the first working diffusion model. Variants of AdaIN are now used in nearly all state-of-the-art diffusion models. My PhD research was supported by Adobe Research Fellowship (2019), Snap Research Fellowship (2019), and NVIDIA Graduate Fellowship (2018).

Selected Publications

CausVid

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

arXiv 2025

Xun Huang, Zhengqi Li, Guande He, Mingyuan Zhou, Eli Shechtman

[arXiv] [Project] [Code]
SSWM

Long-Context State-Space Video World Models

ICCV 2025

Ryan Po, Yotam Nitzan, Richard Zhang, Berlin Chen, Tri Dao, Eli Shechtman, Gordon Wetzstein, Xun Huang

[arXiv] [Project]
CausVid

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

CVPR 2025

Tianwei Yin*, Qiang Zhang*, Richard Zhang, William T. Freeman, Fredo Durand, Eli Shechtman, Xun Huang

[arXiv] [Project] [Code]
Magic3D

Magic3D: High-Resolution Text-to-3D Content Creation

CVPR 2023 (Highlight)

Chen-Hsuan Lin*, Jun Gao*, Luming Tang*, Towaki Takikawa*, Xiaohui Zeng*, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, Tsung-Yi Lin

[arXiv] [Project] [Video]
eDiff-I

eDiff-I: Text-to-Image Diffusion Models with Ensemble of Expert Denoisers

arXiv 2022

Yogesh Balaji, Seungjun Nah, Xun Huang, Arash Vahdat, Jiaming Song, Qinsheng Zhang, Karsten Kreis, Miika Aittala, Timo Aila, Samuli Laine, Bryan Catanzaro, Tero Karras, Ming-Yu Liu

[arXiv] [Project] [Video]
PoE-GANs

Multimodal Conditional Image Synthesis with Product-of-Experts GANs

ECCV 2022

Xun Huang, Arun Mallya, Ting-Chun Wang, Ming-Yu Liu

[arXiv] [Project] [Video] [Two Minute Papers]
PointFlow

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

[arXiv] [Code] [Video]
MUNIT

Multimodal Unsupervised Image-to-Image Translation

ECCV 2018

Xun Huang, Ming-Yu Liu, Serge Belongie, Jan Kautz

[arXiv] [Code] [Video]
AdaIN

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

ICCV 2017 (Oral)

Xun Huang, Serge Belongie

[arXiv] [Code]
SGAN

Stacked Generative Adversarial Networks

CVPR 2017

Xun Huang, Yixuan Li, Omid Poursaeed, John Hopcroft, Serge Belongie

[arXiv] [Code]
* indicates equal contribution.
See Google Scholar for the full list of publications.

Teaching

Student mentees/interns

I have been fortunate to work with many talented students and interns: