A Multi-Modal Benchmark for Biomedical Machine-Learning Agents
Published in Benchmark · manuscript in preparation, 2025
Role: contributing author · Status: in progress.
Design of an AI-agent framework and a curated benchmark to evaluate an agent’s ability to generate correct, runnable code for real biological research tasks across multiple data modalities. Supervised by Prof. Le Song at GenBio AI.
Recommended citation: Yonghan Yang, et al. A Multi-Modal Benchmark for Biomedical Machine-Learning Agents. Manuscript in preparation, 2025–2026.