Yin Fang

I am a postdoctoral fellow at the National Institutes of Health (NIH), supervised by Dr. Zhiyong Lu.

I received my Ph.D. in Computer Science from Zhejiang University in June 2024, supervised by Professors Huajun Chen, Ningyu Zhang, and Xiaohui Fan.

I am a biomedical AI researcher developing computational methods and benchmark resources for biomedical reasoning and data-driven biological discovery. My earlier work centered on molecular learning — knowledge graph-enhanced molecular representation, biomolecular instruction tuning, and molecular generation with feedback — bridging graph neural networks and large language models for chemistry and biology. My current research at NLM/NIH builds biomedical large language models for single-cell reasoning and clinical applications. I am now leading the TrialGPT 2.0 project, NLM/NIH's AI-powered patient-to-clinical-trial matching system.

Email / Google Scholar / DBLP / CV / GitHub / Twitter

Selected Research

Biomedical LLMs

* Equal contribution. Full list: Google Scholar

Selected Research

Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning

Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution

Knowledge Graph-enhanced Molecular Contrastive Learning with Functional Prompt

Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

Domain-Agnostic Molecular Generation with Self-feedback

The Future of Molecular Studies through the Lens of Large Language Models

De Novo Analysis of Bulk RNA-seq Data at Spatially Resolved Single-cell Resolution

Molecular Contrastive Learning with Chemical Element Knowledge Graph

Knowledge-informed Molecular Learning: A Survey on Paradigm Transfer