BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ZContent.net//ZapCalLib 1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
SUMMARY:The bittersweet lesson of scaling in AI for materials
LOCATION:Chemistry A101
TZID:America/Denver
DTSTART:20260417T160000
UID:2026-10-16-18-53-24@natsci.colostate.edu
DTSTAMP:20261016T185324
Description:Seminar Abstract:\nAI offers a powerful opportunity to accelera
 te the discovery of chemicals and materials critical for energy and sustai
 nability\, much as it has transformed other domains. Progress in AI increa
 singly appears to depend on scaling—perhaps above all else. As Rich Sutt
 on’s “bitter lesson” suggests\, methods that effectively harness com
 putation tend to outperform those relying heavily on handcrafted knowledge
 . In chemistry and materials science\, this insight carries both promise a
 nd tension.\n\nThis paradigm is evident in the success of machine learning
  interatomic potentials (MLIPs)\, surrogates for quantum mechanical calcul
 ations. Trained on massive datasets—often containing hundreds of million
 s of samples—these models exhibit scaling behavior similar to that seen 
 in language and vision systems. They generalize to new scientific problems
  and enable simulations that were previously infeasible. Generative models
 \, often trained on similar synthetic data\, can dream new materials. Mean
 while\, debate continues on the role of inductive bias—whether physical 
 constraints are best embedded in model architectures or learned through tr
 aining.\n\nYet MLIPs remain proxies for simulation\, and materials ultimat
 ely matter only when synthesized and deployed at scale. This is the “bit
 ter” reality: translating AI-driven discoveries into real-world impact r
 equires slow\, costly experimental and industrial processes. Our work addr
 esses both extremes—scalable ML-driven simulation and the hands-on chall
 enge of turning AI-designed materials into practical technologies.\nSpeake
 r Bio:\nRafael Gomez-Bombarelli is the Paul M Cook Associate Professor in 
 MIT\\'s Department of Materials Science and Engineering\; and co-founder a
 nd Chief Scientific Officer at Lila Sciences. He earned his undergraduate 
 and graduate degrees in chemistry from the University of Salamanca\, Spain
 \, and conducted postdoctoral research at Heriot-Watt University and Harva
 rd University\, under Alan Aspuru-Guzik. Rafa\\'s research integrates mach
 ine learning with atomistic simulations to expedite the discovery and desi
 gn of novel materials for applications in energy\, sustainability\, and he
 althcare. 4:00 pm
END:VEVENT
END:VCALENDAR