- This event has passed.
CBE Seminar: “Towards Datasets and AI/ML Models for All of Chemistry and Materials Science” (Zack Ulissi, Meta FAIR)
February 11 at 3:30 PM - 4:30 PM
Abstract:
Machine learning models with the accuracy of ab-initio simulations at greatly accelerated speeds are rapidly making progress across chemistry and materials science. This progress has been driven by open science efforts in datasets and new models released by the FAIR Chemistry team and many others in the community. I will discuss the five open dataset efforts released by our team (Open Catalyst, Open Direct-Air Capture, Open Materials, Open Molecular Crystals, and Open Molecules), and specifically the OMol25 dataset released in May comprising >100M organic structures. I will also discuss the Universal Model for Atoms (UMA) trained on all these datasets and sets new standards in accuracy across a number of community benchmarks. All of the work presented is open science, and immediately available for use.
Zack Ulissi
Senior Research Manager
Zack Ulissi is a senior research scientist manager on the FAIR Chemistry team in Meta’s Fundamental AI Research lab and an Adjunct Professor of Chemical Engineering at Carnegie Mellon University. He has led several open science projects and community efforts. Prior to Meta, he was an Associate Professor of Chemical Engineering at CMU. He completed his undergraduate work at the University of Delaware, M.A.St. at Cambridge, PhD at MIT on carbon nanotube devices with Michael Strano and Richard Braatz, and post-doc in catalysis at Stanford with Jens Nørskov.