Skip to content

HKU IDS Scholar

Graduation-cap Home
Professor Bo DAI
Assistant Professor
HKU Musketeers Foundation Institute of Data Science
bdai@hku.hk
P307B, Graduate House, HKU 
Key Expertise
Generative AI; Interactive AI; AI and Creativity; Real-to-Sim-to-Real
About Me
Dr Bo Dai is an Assistant Professor in the Musketeers Foundation Institute of Data Science, The University of Hong Kong. He obtained his PhD degree from The Chinese University of Hong Kong, working with Prof. Dahua Lin. His research interests include Generative AI and its interdisciplinary applications in areas covering Embodied AI, Scientific Discovery, Metaverse and Creativity. His representative works include AnimateDiff, a pioneering work and milestone in video generation, as well as a leading research series in city-scale scene reconstruction and rendering such as CityNeRF, GridNeRF, LandMark, and Scaffold-GS. He is an Area Chair of NeurIPS2024 and AAAI 2021.
Current Research Project
By tackling the fidelity, scalability, controllability and accessibility of generative ai, we aim at empowering machines with human-level imagination, which provides intrinsic initiative for self-improvement, essential foundation for reasoning, new possibility for creativity, as well as technical solution for simulation.
Selected Publications
  1. Yidi Shao, Chen Change Loy, **Bo Dai**, “Learning 3D Garment Animation from Trajectories of A Piece of Cloth”, *Advances in Neural Information Processing Systems (NeurIPS) 2024*.
  2. Kailin Li, Jingbo Wang, Lixin Yang, Cewu Lu, **Bo Dai**, “SemGrasp: Semantic Grasp Generation via Language Aligned Discretization”, *European Conference on Computer Vision (ECCV) 2024,* **Oral**.
  3. Yi Shi, Jingbo Wang, Xuekun Jiang, Bingkun Lin, **Bo Dai**, Xue Bin Peng, “Interactive Character Control with Auto-regressive Motion Diffusion Models”, *ACM Transactions on Graphics (SIGGRAPH 2024).*
  4. Tao Lu, Mulin Yu, Linning Xu, Yuanbo Xiangli, Limin Wang, Dahua Lin, and **Bo Dai**, “Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering”, *IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024*, **Highlight**.
  5. Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and **Bo Dai**, “AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning”, *International Conference on Learning Representation (ICLR) 2024*, **Spotlight**.
  6. Chong Zhou, Chen Change Loy, and **Bo Dai**, “Extract Free Dense Labels from CLIP”, *European Conference on Computer Vision (ECCV) 2022*, **Oral**.
  7. Yidi Shao, Chen Change Loy, **Bo Dai**, “Transformer with Implicit Edges for Particle-based Physics Simulation”, *European Conference on Computer Vision (ECCV) 2022*.
  8. Yuanbo Xiangli, Linning Xu, Xingang Pan, Nanxuan Zhao, Anyi Rao, Christian Theobalt, **Bo Dai**, and Dahua Lin, “Bungeenerf: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering”, *European Conference on Computer Vision (ECCV) 2022*.
  9. **Bo Dai** and Dahua Lin, “Contrastive Learning for Image Captioning”, *Advances in Neural Information Processing Systems (NeurIPS) 2017*.
  10. **Bo Dai**, Sanja Fidler, Raquel Urtasun, and Dahua Lin, “Towards Diverse and Natural Image Descriptions via a Conditional GAN”, *International Conference on Computer Vision (ICCV) 2017*, **Oral**.
Research Interests
Empowering Machines with Human-Level Imagination
Seminar