About me

I'm currently looking for full-time opportunities starting in Fall 2026.

Hi, I am Zeyuan Chen, a PhD candidate at University of California, San Diego, advised by Prof. Zhuowen Tu. My current research focus is on building visual generative models and unified understanding and generation models. I am a Research Intern @ Adobe Firefly with Dr. Yuanjun Xiong and Dr. Mingze Xu, exploring scalable architecture designs for video in Adobe’s next-generation unified generative model.

Previously, I was a Research Intern @ Snap Research, working with Dr. Bing Zhou, Dr. Zhikang Dong, and Dr. Hao Chen this past spring. I was a Research Intern @ Adobe Firefly with Dr. Yuanjun Xiong and Dr. Kai Zhang in summer 2025, and a Research Scientist Intern @ TikTok, working with Dr. Hongyi Xu and Dr. Linjie Luo in summer 2024, and with Dr. Peng Wang and Dr. Kejie Li in summer 2023. I obtained my bachelor’s degree from the School of the Gifted Young at the University of Science and Technology of China, and was fortunate to work with Prof. Xiaolong Wang @ UCSD; Prof. Shenlong Wang @ UIUC; Prof. Zhangyang (Atlas) Wang @ UT Austin and Prof. Dong Liu @ USTC.

Contact: zec016@ucsd.edu · Resume: here

Selected Publications

Soft Tail-dropping for Adaptive Visual Tokenization
Zeyuan Chen, Kai Zhang, Zhuowen Tu, Yuanjun Xiong.
In ECCV 2026.
[PDF],[Code],[Project page]
StreamTalker: Streaming Talking Person Audio-Video Joint Generation
Zeyuan Chen, Zhikang Dong, Vidit Goel, Bing Zhou, Zhenzhi Wang, Jian Wang, Dhritiman Sagar, Sergei Korolev, Zhuowen Tu, Hao Chen.
In submission.
[PDF],[Code],[Project page]
QuadTok: Quad-Tree Visual Tokenizer For Autoregressive Image Generation
Yucheng Mao*, Zeyuan Chen*, Xiang Zhang, Divyansh Srivastava, Bingnan Li, Haiyang Xu, Zhuowen Tu.
In submission.
[PDF],[Code],[Project page]
Central-Peripheral Vision-Inspired Multimodality Models for Spatial Reasoning
Zeyuan Chen, Xiang Zhang, Haiyang Xu, Jianwen Xie, Zhuowen Tu.
In WACV 2026.
[PDF],[Code],[Project page]
X-Dancer: Expressive music to human dance video generation
Zeyuan Chen, Hongyi Xu, Guoxian Song, You Xie, Chenxu Zhang, Xin Chen, Chao Wang, Di Chang, Linjie Luo.
In ICCV 2025 (Highlight).
[PDF],[Code],[Project page]
Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction
Xiang Zhang*, Zeyuan Chen*, Fangyin Wei, Zhuowen Tu.
In ICCV 2023.
[PDF],[Code],[Project page]
CASA: Category-agnostic Skeletal Animal Reconstruction
Yuefan Wu*, Zeyuan Chen*, Shaowei Liu, Zhongzheng Ren, Shenlong Wang.
In NeurIPS 2022.
[PDF],[Code],[Project page]
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
Zeyuan Chen, Yinbo Chen, Jingwen Liu, Xingqian Xu, Vidit Goel, Zhangyang Wang, Humphrey Shi, Xiaolong Wang.
In CVPR 2022.
[PDF],[Code],[Project page]
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors
Zeyuan Chen, Yangchao Wang, Yang Yang, Dong Liu.
In CVPR 2021 (Oral).
[PDF],[Code],[Project page]
CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise
Zeyuan Chen, Yifan Jiang, Dong Liu, Zhangyang Wang.
In IEEE Transactions on Image Processing (TIP).
[PDF],[Code],[Project page]