avatar

Angtian Wang

Research Scientist
ByteDance / TikTok
angtianwang@gmail.com


About Me

I am a Research Scientist at ByteDance working on GenAI. Previously, I earned my Ph.D. in Computer Science from Johns Hopkins University, advised by Bloomberg Distinguished Professor Alan L. Yuille. I have a board research experience in vairent computer vision / artificaial intellegence area, including but not limit to Video Generation 1 2 3, 3D vision 4 5 6, Robust Vision 7 8, Differible Rendering 9, and Medical Image Diagnosis 10 11.

Work Experience

ByteDance, Senior Research Scientist

My main focus is on developing high-quality, controllable, and temporally consistent video generation models. My work covers localized control of video synthesis, ID/IP-conditioned video generation, and long-form video generation, as well as large-scale video foundation model training. I have been deeply involved in building the complete training system for video generation — from raw video collection and processing pipelines, to data loading, model design (DiT-based architectures), and large-scale distributed training. Our research has been successfully deployed in TikTok effect products such as AI Mermaid (best AI effects on TikTok since 2023).

Publications

  1. arXiv Preprint
    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
    ArXiv, 2025.
    PDF Project Page
  2. arXiv Preprint
    ATI: Any Trajectory Instruction for Controllable Video Generation
    Angtian Wang, Haibin Huang, Jacob Zhiyuan Fang, Yiding Yang, Chongyang Ma
    ArXiv, 2025.
    PDF Project Page Code Model
  3. NIPS
    WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
    Zhiheng Liu, Xueqing Deng, Shoufa Chen, Angtian Wang, Qiushan Guo, Mingfei Han, Zeyue Xue, Mengzhao Chen, Ping Luo, Linjie Yang
    Conference on Neural Information Processing Systems (NIPS), 2025.
    PDF PDF Project Page Code
  4. arXiv Preprint
    MAGREF: Masked Guidance for Any-Reference Video Generation
    Yufan Deng, Xun Guo, Yuanyang Yin, Jacob Zhiyuan Fang, Yiding Yang, Yizhi Wang, Shenghai Yuan, Angtian Wang, Bo Liu, Haibin Huang, Chongyang Ma
    ArXiv, 2025.
    PDF PDF Project Page Code Model
  5. AAAI
    HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction
    Angtian Wang, Yuanlu Xu, Nikolaos Sarafianos, Robert Maier, Edmond Boyer, Alan Yuille, Tony Tung
    AAAI Conference on Artificial Intelligence (AAAI), 2024.
    PDF Project Page
  6. WACV
    Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis
    Angtian Wang, Wufei Ma, Alan Yuille, Adam Kortylewski
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
    PDF Project Page
  7. ICLR
    VoGE: A Differentiable Volume Renderer using Neural Gaussian Ellipsoids
    Angtian Wang, Peng Wang, Jian Sun, Adam Kortylewski, Alan Yuille
    IEEE/CVF International Conference on Learning Representations (ICLR), 2023.
    PDF Code
  8. NIPS
    Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose
    Angtian Wang, Shenxiao Mei, Alan Yuille, Adam Kortylewski
    Conference on Neural Information Processing Systems (NIPS), 2021.
    PDF Code
  9. ICLR
    NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation
    Angtian Wang, Adam Kortylewski, Alan Yuille
    International Conference on Learning Representations (ICLR), 2021.
    PDF Code
  10. CVPR
    Robust Object Detection Under Occlusion With Context-Aware CompositionalNets
    Angtian Wang*, Yihong Sun*, Adam Kortylewski, Alan Yuille
    IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2020.
    PDF Code
  11. CVPR
    Structure-Aware Sparse-View X-ray 3D Reconstruction
    Yuanhao Cai, Jiahao Wang, Alan Yuille, Zongwei Zhou, Angtian Wang
    IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024.
    PDF Code
  12. ICLR
    Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos.
    Fengrui Tian, Yueqi Duan, Angtian Wang, Jianfei Guo, Shaoyi Du
    International Conference on Learning Representations (ICLR), 2024.
    PDF Code
  13. ICLR
    Adding 3D Geometry Control to Diffusion Models
    Wufei Ma, Qihao Liu, Jiahao Wang, Angtian Wang, Xiaoding Yuan, Yi Zhang, Zihao Xiao, Guofeng Zhang, Beijia Lu, Ruxiao Duan, Yongrui Qi, Adam Kortylewski, Yaoyao Liu, Alan Yuille
    International Conference on Learning Representations (ICLR), 2024.
    PDF Code Project Page
  14. WACV
    Robust Category-Level 3D Pose Estimation from Synthetic Data
    Jiahao Yang, Wufei Ma, Angtian Wang, Xiaoding Yuan, Alan Yuille, Adam Kortylewski
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
    PDF
  15. ICCV
    3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation
    Yi Zhang, Pengliang Ji, Angtian Wang, Jieru Mei, Adam Kortylewski, Alan Yuille
    International Conference on Computer Vision (ICCV), 2023.
    PDF Code Project Page
  16. WACV
    CoKe: Localized Contrastive Learning for Robust Keypoint Detection
    Yutong Bai*, Angtian Wang*, Adam Kortylewski, Alan Yuille
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.
    PDF
  17. ECCV
    Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features
    Wufei Ma, Angtian Wang, Alan Yuille, Adam Kortylewski
    European Conference on Computer Vision (ECCV), 2022.
    PDF Code
  18. ECCV
    OOD-CV: A Benchmark for Robustness to Individual Nuisances in Real-World Out-of-Distribution Shifts
    Bingchen Zhao, Shaozuo Yu, Wufei Ma, Mingxin Yu, Shenxiao Mei, Angtian Wang, Ju He, Alan Yuille, Adam Kortylewski
    European Conference on Computer Vision (ECCV), 2022.
    PDF Project Page
  19. IJCV
    Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion
    Adam Kortylewski, Qing Liu, Angtian Wang, Yihong Sun, Alan Yuille
    International Journal of Computer Vision (IJCV), 2020.
    PDF Code
  20. MICCAI
    Hyper-Pairing Network for Multi-Phase Pancreatic Ductal Adenocarcinoma Segmentation
    Yuyin Zhou, Yingwei Li, Zhishuai Zhang, Yan Wang, Angtian Wang, Elliot Fishman, Alan Yuille, Seyoun Park
    International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2019.
    PDF
  21. ECCV
    Weakly Supervised Region Proposal Network and Object Detection
    Peng Tang, Xinggang Wang, Angtian Wang, Yongluan Yan, Wenyu Liu, Junzhou Huang, Alan Yuille
    European Conference on Computer Vision (ECCV), 2018.
    PDF
  22. arXiv Preprint
    Learning a Category-level Object Pose Estimator without Pose Annotations
    Fengrui Tian, Yaoyao Liu, Adam Kortylewski, Yueqi Duan, Shaoyi Du, Alan Yuille, Angtian Wang
    arXiv preprint 2024
    PDF
  23. arXiv Preprint
    Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis
    Yuanhao Cai, Yixun Liang, Jiahao Wang, Angtian Wang, Yulun Zhang, Xiaokang Yang, Zongwei Zhou, Alan Yuille
    arXiv preprint 2024
    PDF
  24. arXiv Preprint
    Robust 3D-aware Object Classification via Discriminative Render-and-Compare
    Artur Jesslen, Guofeng Zhang, Angtian Wang, Alan Yuille, Adam Kortylewski
    arXiv preprint 2023
    PDF
  25. arXiv Preprint
    Benchmarking Robustness in Neural Radiance Fields
    Chen Wang, Angtian Wang, Junbo Li, Alan Yuille, Cihang Xie
    arXiv preprint 2023
    PDF

Services

Reviewers


Powered by Jekyll and Minimal Light theme.