👋 About Me
I’m a Research Scientist at Alibaba Wan Team, where I serve as a core contributor of Wan3.0, Wan2.7, Wan2.6 and Wan2.5. I also hold a research position at Zhejiang University, working closely with Prof. Yi Yang. I obtained my Ph.D. in Computer Science from Fudan University, supervised by Prof. Yu-Gang Jiang (IEEE Fellow) and Prof. Zuxuan Wu.
Research Interests
- Alignment reinforcement learning alignment for visual generation (RLHF, preference optimization, reward modeling)
- Generative models text-to-video generation, controllable visual generation, video editing
- Representation learning video understanding, 3D understanding, image retrieval
🔥 News
- 🎈Achieved 1400+ citations on Google Scholar and an h-index of 18.
- Wan Team released Wan 3.0. Feel free to try it out!
- DiffusionOPD accepted to SIGGRAPH ASIA 2026.
- FlashMotion and FlashPortrait accepted to CVPR 2026.
- Wan Team released Wan 2.6. Feel free to try it out!
- Wan Team released Wan 2.5.
- Released StableAvatar and achieved 1000+ GitHub stars.
- AID and MagicMotion accepted to ICCV 2025.
- Defended Ph.D. thesis and awarded Outstanding Graduates of Shanghai!
- Released MagicMotion and achieved 100+ GitHub stars.
- StableAnimator accepted to CVPR 2025 and achieved 1300+ GitHub stars.
- Two papers accepted to NeurIPS 2024.
- “A Survey on Video Diffusion Models” accepted to ACM Computing Surveys.
- Invited talk at Openmmlab about Video Generation Models, [slides].
- SimDA accepted to CVPR 2024.
- Invited talk at Kunlun Research, “A Survey on Video Diffusion Models”.
- Awarded certificate of “Star of Tomorrow” at MSRA.
- Two papers accepted to CVPR 2023.
- Three papers accepted to ECCV 2022.
📝 Publications
A full publication list is available on [Google Scholar][Semantic Scholar]
(*: equal contribution; †: project leader)
Selected Publications
Image Generation
Video Generation
Video Generation
Video Generation
Video Generation
Video Generation
Video Understanding
Other Publications
-
DeRA: Decoupled Representation Alignment for Video Tokenization
-
FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance
-
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
-
ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning
-
Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
-
GenRec: Unifying Video Generation and Recognition with Diffusion Models
-
TranSFormer: Slow-Fast Transformer for Machine Translation
-
Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network
-
Human2Robot: Learning Robot Actions from Paired Human-Robot Videos
-
StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animation
-
AdaDiff: Adaptive Step Selection for Fast Diffusion
-
Advancing Dark Action Recognition via Modality Fusion and Dark-to-Light Diffusion Model
-
Multi-Level Region Matching for Fine-Grained Sketch-Based Image Retrieval
-
3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation
-
CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification
-
From Coarse to Fine: Hierarchical Structure-aware Video Summarization
🎖 Honors and Awards
Below, I exhaustively list some of my Honors and Awards that inspire me a lot.
- 2025 Outstanding graduates of Shanghai Top-1%, PhD
- 2025 Alibaba Star Program and Tencent Qingyun Plan
- 2024 Tencent academic scholarship Top-3%, PhD
- 2023 Fudan University excellent academic scholarship Top-5%, PhD
- 2023 "Star of Tomorrow" intern of MicroSoft Research Asia Top 10%, PhD
- 2022 Tencent academic scholarship Rank 1/130, PhD
- 2021 Fudan University excellent academic scholarship Top-5%, Master
- 2020 Outstanding graduates of TianJin University Top-5%
- 2018 Excellent monitor of Tianjin University Top-10
- 2017-2020 Academic scholarship of Tianjin University Top-10%
💬 Invited Talks
💻 Internships
-
MicroSoft Research Asia2022.03 - 2023.08Visual Computing Group
- Video Diffusion Model
- Video Understanding
🎓 Academic Service
Conference Program Committee
- 2022-2025IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2023-2025IEEE/CVF International Conference on Computer Vision (ICCV)
- 2022-2024European Conference on Computer Vision (ECCV)
- 2024-2025International Conference on Learning Representations (ICLR)
- 2025ACM SIGGRAPH Conference (SIGGRAPH)
- 2024-2025International Conference on Machine Learning (ICML)
- 2024-2025Conference on Neural Information Processing Systems (NeurIPS)
- 2023-2025AAAI Conference on Artificial Intelligence (AAAI)