Zehuan Yuan

Researcher, ByteDance Inc.

Joined

July 2019

Names

Zehuan Yuan

Emails

****@bytedance.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Researcher

ByteDance Inc. (bytedance.com)

2017 – Present

PhD student

Nanjing University (nju.edu.cn)

2012 – 2017

Advisors, Relations & Conflicts

Coauthor

Yi Jiang

2017 – Present

PhD Advisor

Tong Lu

2012 – 2017

Expertise

Large Language Model

Present

Diffusion Model

Present

Deep Learning

Present

Publications

BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
Zhaoyang Li, Dongjun Qian, Kai Su, qishuai diao, Xiangyang Xia, Chang Liu, Wenfei Yang, Tianzhu Zhang, Zehuan Yuan
- ICLR 2026 Poster
- Readers: Everyone
Goku: Generative Flow Kit for Unified Image-Video Creation
Shoufa Chen, Chongjian GE, Yuqi Zhang, Yida Zhang, Fengda Zhu, Hao Yang, Hongxiang Hao, Wuhui, Zhichao Lai, Yifei Hu, Ting-Che Lin, Shilong Zhang, Fu Li, Chuan Li, Xing Wang, Yanghua Peng, Peize Sun, Ping Luo, Yi Jiang, Zehuan Yuan et al. (2 additional authors not shown)
- OpenReview Archive Direct Upload
- Readers: Everyone
UniTok: a Unified Tokenizer for Visual Generation and Understanding
Chuofan Ma, Yi Jiang, Junfeng Wu, Jihan Yang, Xin Yu, Zehuan Yuan, BINGYUE PENG, XIAOJUAN QI
- NeurIPS 2025 spotlight
- Readers: Everyone
InfinityStar: Uniﬁed Spacetime AutoRegressive Modeling for Visual Generation
Jinlai Liu, Jian Han, Bin Yan, Wuhui, Fengda Zhu, Xing Wang, Yi Jiang, BINGYUE PENG, Zehuan Yuan
- NeurIPS 2025 oral
- Readers: Everyone
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Keyu Tian, Yi Jiang, Zehuan Yuan, BINGYUE PENG, Liwei Wang
- NeurIPS 2024 oral
- Readers: Everyone
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Keyu Tian, Yi Jiang, Zehuan Yuan, BINGYUE PENG, Liwei Wang
- arxiv
- Readers: Everyone
Recognize Any Regions
Haosen Yang, Chuofan Ma, Bin Wen, Yi Jiang, Zehuan Yuan, Xiatian Zhu
- NeurIPS 2024 poster
- Readers: Everyone
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
Junke Wang, Yi Jiang, Zehuan Yuan, BINGYUE PENG, Zuxuan Wu, Yu-Gang Jiang
- NeurIPS 2024 poster
- Readers: Everyone
Multi-Level Contrastive Learning for Dense Prediction Task
Qiushan Guo, Yizhou Yu, Yi Jiang, Jiannan Wu, Zehuan Yuan, Ping Luo
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
RegionSpot: Unleashing the Power of Frozen Foundation Models for Open-World Region Understanding
Haosen Yang, Chuofan Ma, Bin Wen, Yi Jiang, Zehuan Yuan, Xiatian Zhu
- Submitted to ICLR 2024
- Readers: Everyone

View all 29 publications

Co-Authors

View all 101 co-authors