Haotian Yang

Researcher, ByteDance Inc.

Joined

May 2021

Names

Haotian Yang (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

ORCID

Career & Education History

Researcher

ByteDance Inc. (bytedance.com)

2025 – Present

Researcher

Kuaishou Technology (kuaishou.com)

2021 – 2025

MS student

Nanjing University (nju.edu.cn)

2018 – 2021

Undergrad student

Nanjing University (nju.edu.cn)

2014 – 2018

Advisors, Relations & Conflicts

Coauthor

Chongyang Ma

2023 – Present

Coauthor

Xin Tao

2024 – 2025

Coauthor

Xintao Wang

2024 – 2025

Coauthor

Haibin Huang

2023 – 2024

Coauthor

Hao Zhu

2018 – 2022

Coauthor

Xun Cao

2018 – 2021

Expertise

3D reconstruction

Present

Deep learning

Present

Video Generation

Present

Motion Capture

Present

Rendering & Animation

Present

Publications

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
Minglei Shi, Ziyang Yuan, Haotian Yang, Xintao Wang, Mingwu Zheng, Xin Tao, Wenliang Zhao, Wenzhao Zheng, Jie Zhou, Jiwen Lu, Pengfei Wan, Di ZHANG, Kun Gai
- Submitted to ICLR 2026
- Readers: Everyone
VMoBA: Mixture-of-Block Attention for Video Diffusion Models
Jianzong Wu, Liang Hou, Haotian Yang, Ye Tian, Pengfei Wan, Di ZHANG, Yunhai Tong
- ICLR 2026 Poster
- Readers: Everyone
Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
Jia Jun Cheng Xian, Muchen Li, Haotian Yang, Xin Tao, Pengfei Wan, Leonid Sigal, Renjie Liao
- Submitted to ICLR 2026
- Readers: Everyone
TGT: Text-Grounded Trajectories for Locally Controlled Video Generation
Guofeng Zhang, Angtian Wang, Jacob Zhiyuan Fang, Liming Jiang, Haotian Yang, Bo Liu, Yiding Yang, Guang Chen, Longyin Wen, Alan Yuille, Chongyang Ma
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Facescape: 3d facial dataset and benchmark for single-view 3d face reconstruction
Hao Zhu, Haotian Yang, Longwei Guo, Yanru Wang, Mingkai Huang, Menghua Wu, Qiu Shen, Ruigang Yang, Xun Cao
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Readers: Everyone
Towards practical capture of high-fidelity relightable avatars
Haotian Yang, Mingwu Zheng, Wanquan Feng, Haibin Huang, Yu-Kun Lai, Pengfei Wan, Zhongyuan Wang, Chongyang Ma
- OpenReview Archive Direct Upload
- Readers: Everyone
VRMM: A Volumetric Relightable Morphable Head Model
Haotian Yang, Mingwu Zheng, Chongyang Ma, Yu-Kun Lai, Pengfei Wan, Haibin Huang
- ACM SIGGRAPH 2024 Conference Papers
- Readers: Everyone
Koala-36m: A large-scale video dataset improving consistency between fine-grained conditions and video content
Qiuheng Wang, Yukai Shi, Jiarong Ou, Rui Chen, Ke Lin, Jiahao Wang, Boyuan Jiang, Haotian Yang, Mingwu Zheng, Xin Tao, Fei Yang, Pengfei Wan, Di ZHANG
- IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2025
- Readers: Everyone
Physically Based Facial Texture Generation in the Wild
Chi Wang, Junming Huang, Rong Zhang, Haotian Yang, Pengfei Wan, Haibin Huang, Chongyang Ma, Weiwei Xu
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Readers: Everyone
Kinda-45M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content
Qiuheng Wang, Yukai Shi, Jiarong Ou, Rui Chen, Ke Lin, Jiahao Wang, Boyuan Jiang, Haotian Yang, Mingwu Zheng, Xin Tao, Fei Yang, Pengfei Wan, Di ZHANG
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

View all 11 publications

Co-Authors

View all 59 co-authors