I am a Research Professor at Hangzhou Institute of Medicine, Chinese Academy of Sciences, and Associate Director of the Medical AI Center. Previously, I served as a Hundred Talents Program Research Professor at the Zhejiang University-Zhijiang Laboratory Platform. I received my Ph.D. in Computer Science and Engineering from The Chinese University of Hong Kong.

My research focuses on developing next-generation computational tools for medical AI and drug discovery, with particular emphasis on leveraging modern artificial intelligence methods, especially large language models, to accelerate pharmaceutical research and development. My research follows a comprehensive pipeline: processing clinical multimodal information to uncover disease mechanisms, and subsequently designing targeted therapeutics to modulate biological functions. I lead a team developing intelligent platforms for drug discovery and have achieved breakthroughs in core algorithms for drug virtual screening workflows, including protein representation, pocket detection, conformational docking, molecular generation, and activity scoring.

I have published over 40 papers as first or corresponding author in prestigious journals and conferences including Nature Machine Intelligence, Nature Computational Science, Nature Communications, ICML, ICLR, and NeurIPS. I currently lead several major research projects including National Key R&D Program International Cooperation Projects and National Natural Science Foundation projects.

News

• 2025.01: “PhyloTune: An efficient method to accelerate phylogenetic updates using a pretrained DNA language model” accepted at Nature Communications
• 2025.01: “DivPro: diverse protein sequence design with direct structure recovery guidance” accepted at Bioinformatics
• 2025.01: “Small CAG Repeat RNA Forms a Duplex Structure with Sticky Ends That Promote RNA Condensation” accepted at Journal of the American Chemical Society
• 2025.01: “MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding” accepted at AAAI 2025
• 2025.01: “Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer” accepted at AAMAS 2025