Shen Sang 桑燊

I am a Senior Research Scientist, with a primary focus on GenAI, at the Intelligent Creation Team, TikTok.

I received my master's degree from UC San Diego. I was fortunate to work with Prof. Manmohan Chandraker at the Visual Computing Center.


shen.sang[at]bytedance[dot]com

profile photo
News

[2026.02] ✨ Lynx is accepted to CVPR 2026.

[2025.09] Lynx is released, feel free to try our latest personalized video generation model!

[2025.02] COAP and ID-Patch are accepted to CVPR 2025.

Show More ▼

Research

I currently work on world models, video generation, and editing, with a focus on building generative models that understand and synthesize dynamic visual content. Over the past few years, I have worked extensively on personalized image and video generation, while also exploring efficient training and inference methods. Prior to this, my research focused on 3D vision and graphics, particularly in areas such as 3D reconstruction and neural relighting.

✨ Video-As-Prompt: Unified Semantic Control for Video Generation
Yuxuan Bian, Xin Chen, Zenan Li, Tiancheng Zhi, Shen Sang, Linjie Luo, Qiang Xu

ICLR, 2026
[project] [arXiv] [code]
✨ Lynx: Towards High-Fidelity Personalized Video Generation
Shen Sang*, Tiancheng Zhi*, Tianpei Gu, Jing Liu, Linjie Luo

CVPR, 2026
[project] [arXiv] [code]
COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
Jinqi Xiao, Shen Sang, Tiancheng Zhi, Jing Liu, Qing Yan, Yuqian Zhang, Linjie Luo, Bo Yuan

CVPR, 2025
[project] [arXiv] [code]
ID-Patch: Robust ID Association for Group Photo Personalization
Yimeng Zhang, Tiancheng Zhi, Jing Liu, Shen Sang, Liming Jiang, Qing Yan, Sijia Liu, Linjie Luo

CVPR, 2025
[project] [arXiv] [code]
ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs
Jiteng Mu, Shen Sang, Nuno Vasconcelos, Xiaolong Wang

ICCV, 2023
[project] [arXiv] [code]
AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging
Shen Sang, Tiancheng Zhi, Guoxian Song, Minghao Liu, Chunpong Lai, Jing Liu, Xiang Wen, James Davis, Linjie Luo

SIGGRAPH Asia, 2022
[project] [paper] [arXiv] [bibtex]
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets
Zhengqin Li, Ting-Wei Yu, Shen Sang, Sarah Wang, Meng Song, Yuhan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh Gundavarapu, Jia Shi, Sai Bi, Zexiang Xu, Hong-Xing Yu, Kalyan Sunkavalli, Miloš Hašan, Ravi Ramamoorthi, Manmohan Chandraker

CVPR, 2021   (Oral Presentation)
[project] [paper] [dataset]
Single-Shot Neural Relighting and SVBRDF Estimation
Shen Sang, Manmohan Chandraker

ECCV, 2020
[project] [paper] [code] [bibtex]
Products

TikTok AI-Moji

2024

AI-powered emoji avatars that transform user selfies into expressive digital characters.

TikTok AI Self

2024

AI-powered self-portrait avatars that generate photorealistic digital characters.

TikTok AI Avatars

2023

AI-powered avatar generation that creates stylized digital characters.

TikTok Avatars

2022

Customizable digital avatars that represent your personality and style.

Service

CVPR (2023-2025), ICCV (2023), ICLR (2023), AAAI (2023-2024), SIGGRAPH (2025), SIGGRAPH Asia (2023), TMM, C&G


Based on Jon Barron's template and enhanced by OpenAI Codex.