I am Jiangning Zhang (张江宁), currently working as a expert researcher of two centers at YouTu Lab, Tencent, Shanghai (技术大咖计划), also serve as the leader for APRIL-AIGC direction. I receive Ph.D. degree in College of Control Science and Engineering, Zhejiang University, Hangzhou, China, under the supervision of Prof. Yong Liu. My research interests include:
🌱 Multimodal Perception and Generation: 🎋 Image/Video Generation/Editing 🎋 Long-term Efficient Video Understanding/RAG 🎋 Agent Applications 🎋 Interdisciplinary Fundamental Researches.
🌱 Efficient Learning: 🥝 Neural Architecture Design 🥝 Light-weight (Ultra-High Definition) Image/Video Model 🥝 Efficient Training/Finetuning.
🌱 Embodied AI: 🍉 World Model 🍉 Sim2Real2Sim 🍉 VLA with Humanoid/Quadruped/Wheeled Robots 🍉 Action Transfer

🔥🔥🔥 我正在寻找具备自驱力的2027级硕士研究生、直博生、博士生,以及科研实习生、科研助理与博士后加入刘勇教授课题组,有上述研究方向相关科研经历者优先考虑。 🔥🔥🔥
🔥🔥🔥 I am looking for self-motivated prospective master students, direct-entry PhD students, PhD students (2027 intake), as well as research interns, research assistants and postdoctoral fellows to join Prof. Yong Liu’s research group. Candidates with research experience in the aforementioned research areas will be given priority. 🔥🔥🔥

🔥 News

  1. 🔥🔥🔥 Checkout our recent T3-Video (Transform Trained Transformer) for Accelerating Naive 4K Video Generation.
  2. 🔥🔥🔥 Checkout our recent Soul for High-fidelity Long-term Multimodal Animation.
  3. 🔥🔥🔥 Checkout our recent OpenVE-3M for High-Quality Instruction-Guided Video Editing.
  4. 🔥🔥🔥 Checkout our recent IVEBench for Instruction-Guided Video Editing Assessment.
  5. 2025.12.08:  🎉🎉🎉 Our team obtains the grand champion🥇🥇🥇 of the offline competition in ATEC 2025 • AI & Robotics Real-World Challenges (US$150,000 prize).
  6. 2025.11.08:  🎉🎉🎉 UltraGen and AdaKD (Oral) are accepted by AAAI 2026.
  7. 2025.09.21:  🎉🎉🎉 ImitDiff is accepted by RA-L 2025.
  8. 2025.09.19:  🎉🎉🎉 AdaVideoRAG and UltraVideo are accepted by NeurIPS 2025.
  9. 2025.08.08:  🎉🎉🎉 MVAD is accepted by TMM 2025.
  10. 2025.07.26:  🎉🎉🎉 EMOv2 is accepted by T-PAMI 2025.
  11. 2025.07.12:  🎉🎉🎉 M3DM-NR is accepted by T-PAMI 2025.
  12. 2025.07.11:  🎉🎉🎉 ADer, FiSeCLIP, and PointSeg are accepted by ICCVW 2025.
  13. 2025.07.06:  🎉🎉🎉 StrandDesigner is accepted by ACM MM 2025.
  14. 2025.06.26:  🎉🎉🎉 LLaVA-KD, CoLVA, and DeT are accepted by ICCV 2025.
  15. 2025.06.05:  🎉🎉🎉 MMoFusion is accepted by PR 2025.
  16. 2025.02.27:  🎉🎉🎉 IAR, MobileMamba, GroundingFace, TIMotion, AnyMaker, Real-IAD D³, SVFR, OSV, EditFT, and Sonic are accepted by CVPR 2025, ranked 14th globally.
  17. 2025.01.29:  🎉🎉🎉 ViTAD is accepted by CVIU 2025.
  18. 2025.01.22:  🎉🎉🎉 SaRA is accepted by ICLR 2025.
  19. 2024.12.10:  🎉🎉🎉 PointRWKV, ID-Sculpt, PCM, and RefLDMSeg are accepted by AAAI 2025.
  20. 2024.09.26:  🎉🎉🎉 MotionBooth, Fetch-and-Forge, and MambaAD are accepted by NeurIPS 2024.
  21. 2024.07.16:  🔥🔥🔥 Checkout our recent MotionMaster, a training-free camera-motion transferred video generation method.
  22. 2024.07.16:  🎉🎉🎉 MotionMaster, MambaGesture, and MDT-A2G are accepted by ACM MM 2024.
  23. 2024.07.01:  🎉🎉🎉 LSFA, FreeMotion, AdaCLIP, TexDreamer (Oral), Face-Adapter, and DiffuMatting are accepted by ECCV 2024, ranked 72th globally.
  24. 2024.06.16:  🎉🎉🎉 ReferenceTwice for few-shot IS is accepted by T-PAMI 2024.
  25. 2024.06.01:  🎉🎉🎉 GPT-4V-AD and CLIP-AD are accepted by IJCAI 2024.
  26. 2024.04.17:  🎉🎉🎉 UniM-OV3D is accepted by IJCAI 2024.
  27. 2024.04.17:  🔥🔥🔥 We release a visual Anomaly Detection toolbox ADer.
  28. 2024.03.20:  🔥🔥🔥 We release the largest industrial anomaly detection dataset Real-IAD.
  29. 2024.02.27:  🎉🎉🎉 Real-IAD, PortraitBooth, SuperSVG, and ROVI are accepted by CVPR 2024.
  30. 2024.02.12:  🎉🎉🎉 Strong backbone EATFormer is accepted by IJCV 2024.
  31. 2024.01.30:  🎉🎉🎉 One paper is accepted by T-PAMI 2024.
  32. 2023.12.14:  🎉🎉🎉 One paper is accepted by ICASSP 2024.
  33. 2023.12.09:  🎉🎉🎉 Four papers are accepted by AAAI 2024.
  34. 2023.07.26:  🎉🎉🎉 Two papers are accepted by ACM MM 2023.
  35. 2023.07.14:  🎉🎉🎉 Four papers are accepted by ICCV 2023.
  36. 2023.07.08:  🎉🎉🎉 One paper is accepted by IJCV 2023.
  37. 2023.07.07:  🎉🎉🎉 One paper is accepted by TIP 2023.
  38. 2023.05.13:  🎉🎉🎉 1st place for Zero-shot Track and 4th place for Few-shot Track in Visual Anomaly and Novelty Detection (VAND) 2023 Challenge by CVPR 2023.
  39. 2023.03.09:  🎉🎉🎉 Six papers are accepted by CVPR 2023.
  40. 2022.11.22:  🎉🎉🎉 One paper is accepted by AAAI 2023.
  41. 2022.11.11:  🎉🎉🎉 One paper is accepted by PRL 2022.
  42. 2022.10.11:  🎉🎉🎉 Happy graduation! 🎉🎉🎉 Working in Tencent Youtu Lab, Shanghai. 🔭🔭🔭
  43. 2022.10.01:  🎉🎉🎉 One paper is accepted by ACM TOG 2022.
  44. 2022.08.17:  🎉🎉🎉 One paper is accepted by TMM.
  45. 2022.07.09:  🎉🎉🎉 Three papers are accepted by ECCV 2022.
  46. 2022.06.18:  🎉🎉🎉 One paper is accepted by TCSVT.
  47. 2022.06.07:  🎉🎉🎉 One of five finalists for the IJIRA Best Paper Award 2022.
  48. 2022.04.21:  🎉🎉🎉 One paper is accepted by IJCAI 2022.
  49. 2022.03.03:  🎉🎉🎉 One paper is accepted by CVPR 2022.
  50. 2021.12.01:  🎉🎉🎉 One paper is accepted by AAAI 2022.
  51. 2021.09.29:  🎉🎉🎉 One paper is accepted by NeurIPS 2021.
  52. 2021.09.27:  🎉🎉🎉 One paper is presented in SPL 2021.
  53. 2021.08.12:  🎉🎉🎉 One paper is presented in TNNLS 2021.
  54. 2021.07.23:  🎉🎉🎉 One paper is presented in ICCV 2021.
  55. 2020.12.12:  🎉🎉🎉 Research intern in YouTu Lab, Tencent, mentored by Researcher Yabiao Wang and Dr. Ying Tai.
  56. 2020.07.03:  🎉🎉🎉 One paper is accepted by ECCV 2020 as spotlight presentation.
  57. 2020.04.01:  🎉🎉🎉 Pursuing Ph.D. in Zhejiang University, under the supervision of Prof. Yong Liu. 🔭🔭🔭
  58. 2020.02.27:  🎉🎉🎉 Two papers are accepted by CVPR 2020.
  59. 2020.01.25:  🎉🎉🎉 One paper is accepted by ICASSP 2020.