Insilico's 2.6B Model Sets New Retrosynthesis SOTA

Insilico Medicine fine-tuned Liquid AI's 2.6B LFM2.5-2.6B in its open-sourced MMAI Gym on 46 million reactions, producing insilicoSOTAFM, which set a new single-step retrosynthesis SOTA.

2026-09-03 ~ 2026-09-04 · 3 related posts

• Insilico puts Liquid AI's 2.6B model into MMAI Gym, setting SOTA in retrosynthesis — helloiamleonie · 2026-09-03
• Insilico's 2.6B Liquid AI-based model sets SOTA in single-step retrosynthesis on 46M reactions — JosephJacks_ · 2026-09-04
• Insilico's customized 2.6B Liquid AI model sets SOTA in retrosynthesis — JosephJacks_ · 2026-09-04