A while ago we figured out that structure enables data-driven design: if we have data of designs + rewards, we can find a design with *higher* reward if we learn a structured function: arxiv.org/abs/2401.05442 In our latest work, @kuba_AI developed a practical model based on this idea that designs materials to optimize target properties. Kuba (@kuba_AI) AI can optimize materials 🤘 Our (@pabbeel, @svlevine, @AIatMeta) proposed transformer model 𝗖𝗹𝗶𝗾𝘂𝗲𝗙𝗹𝗼𝘄𝗺𝗲𝗿, combined with 𝗲𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 strategies, discovers materials that optimize target properties. arxiv.org/abs/2603.06082 — https://nitter.net/kuba_AI/status/2033382617442345321#m

→ View original post on X — @berkeley_ai, 2026-03-21 03:11 UTC