About Me关于我

I am an Algorithm Researcher at Tongyi Lab, Alibaba Group. I received my M.S. degree from the Department of Automation, Tsinghua University in 2020, advised by Prof. Changshui Zhang. I joined Alibaba in 2023.

My research focuses on building unified foundation models for the natural sciences. I am particularly interested in scientific generative modeling, cross-modal representation learning, and developing scalable agent systems for complex scientific workflows.

我是阿里巴巴通义实验室算法研究员。2020 年硕士毕业于清华大学自动化系，师从张长水教授，2023 年加入阿里巴巴。

研究兴趣集中在构建面向自然科学的统一基础模型，特别是科学生成建模、跨模态表示学习，以及面向复杂科学工作流的可扩展 Agent 系统。

Research Interests:研究方向：

• AI for Science — Unified Foundation Models
  Building general-purpose generative models that natively handle scientific entity within a single LLM framework.构建原生处理蛋白质、分子、反应、材料的通用生成模型，运行在统一 LLM 框架内。
• Scientific Agent Training
  Training agents with domain-specific scientific reasoning and tool-use capabilities.训练具备领域科学推理和工具调用能力的 Agent。
• Agent Harness Engineering
  Building stronger scaffolds to unlock frontier agent capabilities for scientific discovery.构建更强的脚手架以释放前沿 Agent 在科学发现中的能力。

🔥 News动态

• 2026.06LOGOS team featured in overseas interview.LOGOS 团队参加海外访谈节目。 [YouTube] [Substack] [X] [LinkedIn]
• 2026.06Released LOGOS — a unified generative foundation model for science.发布科学语言统一模型 LOGOS。 [WeChat公众号]
• 2026.06LOGOS technical report released on arXiv.LOGOS 技术报告发布于 arXiv。
• 2026.05Caduceus accepted by SIGKDD 2026.Caduceus 被 SIGKDD 2026 接收。
• 2026.01DrugTrail accepted by ICLR 2026.DrugTrail 被 ICLR 2026 接收。
• 2025.02GENERator preprint released.GENERator 预印本发布。

📖 Education教育背景

• 2017 - 2020 ｜ M.S., Department of Automation, Tsinghua University — Pattern Recognition & Intelligent Systems (Advisor: Prof. Changshui Zhang)清华大学 自动化系 模式识别与智能系统 硕士（导师：张长水教授）
• 2013 - 2017 ｜ B.E., School of Automation Science and Electrical Engineering, Beihang University — Control Science and Engineering北京航空航天大学 自动化科学与电气工程学院 控制科学与工程 本科

📝 Selected Publications代表性论文

• Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
  M Li, Y Liu, J Ye, B Su, JR Wen, Z Wang
  arXiv preprint arXiv:2606.16905, 2026
  PaperCode
• GENERator: A Long-Context Generative Genomic Foundation Model
  W Wu, Q Li, Y Zhang, Z Zhan, R Chen, M Li, K Fu, J Qi, Y Bao, C Wang, ...
  arXiv preprint arXiv:2502.07272, 2025
  PaperCode
• Caduceus: MoE-enhanced Foundation Models Unifying Biological and Natural Language
  A M Yin, Y Zhu, J Wu, J Ma, H Zhou, M Li, Y Zhou, J Chen, T Hou, J Ye
  ACM SIGKDD 2026
• DrugTrail: Interpretable Drug Discovery via Structured Reasoning and Druggability-Tailored Preference Optimization
  Y Liu, M Li, X Zhu, R Jiao, Y Dong, X Tang, Y Liu, J Ye, B Su, Z Wang
  ICLR 2026
• ProtCLIP: Function-informed Protein Multi-modal Learning
  H Zhou, M Yin, W Wu, M Li, K Fu, J Chen, J Wu, Z Wang
  AAAI 2025
• Synergy of GFlowNet and Protein Language Model Makes a Diverse Antibody Designer
  M Yin, H Zhou, Y Zhu, J Wu, W Wu, M Li, K Fu, Z Wang, CY Hsieh, T Hou, ...
  AAAI 2025
• A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery
  Y Zhu, M Li, J Liu, K Fu, J Wu, Q Li, M Yin, J Ye, J Wu, Z Wang
  arXiv preprint arXiv:2503.04362, 2025
  PaperCode
• Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
  Y Zhu, J Wu, Q Li, J Yan, M Yin, W Wu, M Li, J Ye, Z Wang, J Wu
  NeurIPS 2024
• CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization
  W Hu, Z Che, N Liu, M Li, J Tang, C Zhang, J Wang
  IEEE TNNLS 35(8), 11595-11607, 2023
• Diversity in Neural Architecture Search
  W Hu, M Li, C Yuan, C Zhang, J Wang
  IJCNN 2020

💻 Projects开源项目

📮 Contact联系

Feel free to reach out for collaborations or discussions. 欢迎就合作与研究问题联系交流。

📧 liyu394194596@qq.com