Grounding, verification-aware scientific agents, mission-held-out space biology, and laboratory-agent evaluation.
JangKeun Kim
jang1563
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
jang1563/agentic-drug-discovery-system updated a dataset 2 days ago
jang1563/bioreview-bench published a dataset 3 days ago
jang1563/bioreview-benchOrganizations
Grounding, verification-aware scientific agents, mission-held-out space biology, and laboratory-agent evaluation.
Auditable benchmarks for scientific agents: drug development decisions, calibrated abstention, tool use, and specialist-model reliability.
Spaceflight biomedical benchmarks and omics / foundation-model resources across NASA, JAXA, and Inspiration4 missions.
Dual-use analysis, biosafety classifiers, over-refusal calibration, and constitutional / agent safety for biological AI.