Me
Haitao Lin (林海涛)
Research Scientist @ Hunyuan, Tencent

About

I am a research scientist in multimodality generative model in HY Fundamental Model Department, Tencent. Before that, I was a CS Ph.D student at Westlake University, joint with Zhejiang University. I obtained my B.S. degree in Solid State Physics from Sichuan University. My research interests focus on generative models, especially in diffusion models with acceleration and distillation techniques. I have been working on their applications in AI4Science, including biomolecule generation and continuous flow fields during my Ph.D.

Education

Ph.D.           Sep. 2021 - Jun. 2026
                     - Westlake University & Zhejiang University, Hangzhou, China
                     - Ph.D. student in Computer Science;
                     - Under the supervision of Stan Z. Li

News

  • I am honored to have contributed to the release of HY-Image 3.5 Preview in joint few-step distillation & RL tuning.
  • Congratulations to my Ph.D. thesis defense!
  • I will join HY, TEG, Tencent as a research scientist in multimodality generative modeling.
  • Three papers (ESC, SYNC, SteinsGate ) are accepted by ICLR 2026.
  • Three papers (CBGBench, EVA, SimDDG) are accepted by ICLR 2025, with CBGBench as spotlight presentation.
  • One paper (EDTPP) is finally accepted by IEEE TKDE after 3 years of review process from my first year of Ph.D.
  • One paper (DiffBP) is accepted by Chemical Science.
  • One paper on Lead Optimization is accepted by Journal of the American Chemical Society.
  • Four papers (PPFlow; GeoAB; Prompt-DDG; Re-Dock) are accepted by ICML 2024, with Re-Dock as spotlight presentation.
  • One paper (MAPE-PPI) is accepted by ICLR 2024, as a spotlight presentation.
  • Two papers (PSC-CPI; SAO) are accepted by AAAI 2024.
  • One paper (D3FG) is accepted by NeurIPS 2023.

Blogs

Experiences

  • May. 2026 - Present
        - Hunyuan, TEG, Tencent, Shanghai, China
        - Research Scientist, working on multimodality generative model;
    		•
  • Apr. 2024 - Aug. 2025
        - DP Technology, Beijing, China
        - Research Intern, working on Biomolecule Generation;
        - Under the guidance of Zhifeng Gao and Guolin Ke
  • Jul. 2019 - Aug. 2019
        - CBICR, Tsinghua University, Beijing, China
        - Visiting Student, working on Neural Science with ML;
        - Supervisor: Quan Wen
    		•

    Selected Publications

    Fundamental Generative Modeling:
  • On the Design of One-step Diffusion via Shortcutting Flow Paths
    •      Lin, H., Hu, P., Ren, M., Gao, Z., Ma, ZM., Ke, G., Wu, T., Li, SZ.
         International Conference on Learning Representations, 2026
         [Paper]      [Code]
  • Conditional Local Convolution for Spatio-temporal Meteorological Forecasting
    •      Lin, H., Gao, Z., Xu, Y., Wu, L., Li, L., Li, SZ.
         AAAI Conference on Artificial Intelligence, 2022
         [Paper]      [Code]
  • Exploring Generative Neural Temporal Point Process
    •      Lin, H., Wu, L., Zhao, G., Liu, P., Li, SZ.
         Transaction on Machine Learning Research, 2022
         [Paper]      [Code]
    Generative Modeling for Molecule Design:
  • CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
    •      Lin, H., Zhao, G., Zhang, O., Huang, Y., Wu, L., Tan, C., Liu, Z., Gao, Z., Li, SZ.
         International Conference on Learning Representations, 2025 (Spotlight, Top 2.0%)
         [Paper]      [Code]
  • DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding
    •      Lin, H., Huang, Y., Zhang, O., Ma, S., Liu, M., Li, X., Wu, L., Ji, S., Hou, T., Li, SZ.
         Chemical Science, Royal Society of Chemistry, 2024
         [Paper]      [Code]
  • Target-Aware Peptide Design with Torsional Flow Matching
    •      Lin, H., Zhang, O., Zhao, H., Jiang, D., Wu, L., Liu, Z., Huang, Y., Li, SZ.
         International Conference on Machine Learning, 2024
         [Paper]      [Code]
  • Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration
    •      Lin, H., Huang, Y., Zhang, O., Liu, Y., Wu, L., Li, S., Chen, Z., Li, SZ.
         Neural Information Processing Systems, 2023
         [Paper]      [Code]

    Selected Honors & Awards

    • National Scholarship, 2016
    • National Scholarship, 2017

    Miscellaneous

    I enjoy cooking, brewing coffee, and spending time with my family and my cats (Edamame the Bicolor Garfield and Pinenut the British Golden Longhair).
    Top