Ziyang Song
Avatar of Ziyiang Song
Assistant Professor
School of Electrical Engineering and Computer Science (EECS)

Ohio University

Athens, Ohio, United States
Email:
Google Scholar | LinkedIn | Xiaohongshu

Biography.

Research Directions. My research focuses on AI for health, with the goal of developing trustworthy and translational AI to address biomedical challenges.

  1. Trustworthy LLMs in Healthcare: I develop methods to improve explainability, uncertainty quantification, and risk control for biomedical LLMs and multi-agent clinical systems.
  2. Foundation Models for Longitudinal Health Data: I design foundation models for irregular and longitudinal healthcare data, including electronic medical records, laboratory measurements, and biosignals.
  3. Interpretable AI for Population Health: I develop probabilistic models and scalable statistical inference methods to learn interpretable representations from electronic health records and genotype data, supporting phenotyping, incidence prediction, and gene discovery.
  4. Generative AI for Biology: I develop foundation models for irregular single-cell RNA-seq time-series data and study domain adaptation methods that leverage unlabeled data.

Lab Opening. I am not currently recruiting Ph.D. students.

Research Interns:
  • We welcome both undergraduate and graduate interns from Ohio University and other institutions.

Collaboration with Me. I am open to external opportunities for invited talks, research collaborations, and part-time consulting employment.

✈ News and Travel

[Aug 2026] Our SafeRx-Agent work, SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation, is accepted at the EMNLP 2026 main conference.

[Aug 2026] I was selected as a Human-First AI Initiative Faculty Fellow at Ohio University.

[Jul 2026] I was awarded the Tinker Research Grant from Thinking Machines Lab.

[May 2025] I received Google Cloud Research Credits to support our research on trustworthy LLM in healthcare.

[Apr 2026] I presented an oral talk, Toward Trustworthy LLMs in Healthcare with Medical Ontologies, at the OSC Research Symposium & NSF AI Workshop.

[Mar 2026] I presented an oral talk and poster, Toward Trustworthy LLMs in Healthcare with Medical Ontologies, at the 2026 Global AI Youth Forum.

[Jan 2026] PheCode-guided multi-modal topic modeling of electronic health records improves disease incidence prediction and GWAS discovery from UK Biobank is accepted at Briefings in Bioinformatics!

[Dec 2025] I was awarded the NVIDIA Academic Grant Program Award (Fall 2025).

[Dec 2025] SMI: Semantic Medical ID for Hierarchy-Aware Concept Representation is accepted at the NeurIPS 2025 ResponsibleFM Workshop.

[Oct 2025] Our TrajGPT work is accepted at IEEE Journal of Biomedical and Health Informatics (J-BHI).

[Sep 2025] Our TimelyGPT work is accepted at journal Health Information Science and Systems.

[Aug 2025] I joined School of EECS at Ohio University as Assistant Professor.

[May 2025] I Completed my Ph.D. degree at McGill University.

🏅 Honors, Awards, and Research Support

Research Grants and Support (as PI)
Selected Honors and Awards