LLMs may be near SOTA at analyzing small molecules, researchers argue
proteinrosh · x · 2026-11-04
Researchers debate whether LLMs are close to SOTA for small-molecule analysis. Evidence cited includes an impressive recent paper, Leash Bio's DEL-screen-based search example, and the replier's own simpler replication experiment using docking scores — inspired by a Rowan blog post — which reached similar conclusions. The tone: the field is still "mostly vibes," but LLMs' small-molecule analysis abilities look genuinely strong.
Related event: LLMs near SOTA on small-molecule optimization, but slow(3 posts)→
More from Research
- History Forcing: Zhejiang U & Microsoft Fix Long-Horizon Drift in Video World Models — ZhejiangUniversity · 2026-11-04
- D&A: Decoupling Description from Assessment Turns Any VLM into a Robot Reward Model — weichiuma · 2026-11-04
- Muon beats AdamW in pretraining loss, but AdamW wins after finetuning at scale — AdtRaghunathan · 2026-11-04
- Vorelios (YC F26) launches AI that predicts physics in seconds to engineer designs autonomously — KlausCodes · 2026-11-04
- Repeated-data pretraining favors smaller batches, finds Sewon Min's GPU-time tradeoff study — sewon__min · 2026-11-04
- Recreating 1992 magnetic-drop sunflower spirals: golden angle emerges from one rule — JosephJacks_ · 2026-11-04