Researchers at MIT introduced BoltzGen, a generative AI model designed to propose novel small molecules for hard‑to‑drug targets, presenting the work at the Abdul Latif Jameel Clinic for Machine Learning in Health. The team, led by Hannes Stärk and collaborators, demonstrated model capabilities in proposing chemically valid candidates and discussed integration with experimental screening workflows. Generative molecular models use learned chemical patterns to output candidate structures; BoltzGen aims to shorten the ideation loop between computational design and lab validation. The group emphasized open collaboration across academia and industry to refine validation pipelines and reduce false leads.