Funding & Grant:

• NAIRR-1370 (NVIDIA): $ 460,000

Research Interest:

• AI For Biology: Now, my research focuses on accelerating scientific discovery with AI in the biological domain.
  • Pre-training:  Developing biological foundation models [GenomeOcean];
  • Post-training: Applying foundation models to enable scientific discoveries [DNABERT-S];
  • Serving: Creating easy-to-use model serving systems to support biological scientists [GenomeBridge].
• LLM Theory: Previously, my research focused on deepening the theoretical understanding of machine learning methods and providing insights to guide the design of new approaches [ICML25'a, ICML25'b, ICLR25, NeurIPS24].

Publications:

• [2025-05-01] Two papers [ICML25'a, ICML25'b] accepted by ICML 2025.
• [2025-04-07] One paper accepted by Bioinformatics & ISMB 2025.
• [2025-01-22] One paper accepted by ICLR 2025.
• [2024-09-25] One paper accepted by NeurIPS 2024.

Invited Talks:

• [2024-03-14] Debora Marks Lab in Harvard Medical School.  
  • DNABERT-S: Learning Species-aware DNA Embedding with Genome Foundation Models.

Internship:

• Quest Diagnostics (2025 Summer).
  • Machine Learning Researcher: develop foundation models for genomics analysis.