Resume
Academic Achievements
- Published multiple papers at top-tier conferences including CVPR, NeurIPS, ACL, ECCV, AAAI, and MM
- Over 5,000 citations in total
- GitHub open-source projects received more than 30,000 likes
- Key works include: NUWA (ECCV 2022), NUWA-Infinity (NeurIPS 2022), NUWA-LIP (CVPR 2023), NUWA-3D (IJCAI 2023), NUWA-XL (ACL 2023), DragNUWA (2023), LayoutNUWA (ICLR 2024), Qwen-Image (2025), etc.
- Multimodal understanding models: Bridge-Tower (AAAI 2023), Manager-Tower (ACL 2023)
- Multimodal systems: Visual ChatGPT (2023), TaskMatrix.AI (Intelligent Computing 2024)
Research Experience
- Currently a senior expert at Tongyi Lab, Alibaba
- Led the development of multimodal generation models: NUWA series (NUWA, NUWA-Infinity, NUWA-XL, DragNUWA, etc.)
- Led Step-Video series (Step-Video-T2V, Step-Video-TI2V) and Qwen-Image
- Developed multimodal understanding models: Bridge-Tower series (KD-VLP, Bridge-Tower)
- Built multimodal dialogue systems: Visual ChatGPT and TaskMatrix.AI