Meet IBM’s new family of AI models for materials discovery
News
Kim Martineau
Materials Discovery
It can take over 10 years to come up with new materials. At IBM Research, we’re looking to accelerate the discovery process using new AI methods, robotics, the hybrid cloud, and quantum computers. Our goal is to unlock new properties and materials to address global challenges in years not decades.
Our work
A new tool for accelerating the discovery of new materials
ResearchPeter HessResolving the odd-number cyclo[13]carbon
Technical noteLeo Gross and Florian AlbrechtResolving the first anti-aromatic carbon allotrope
Technical noteLeo GrossAn AI foundation model that learns the grammar of molecules
NewsPayel Das, Youssef Mroueh, Inkit Padhi, Vijil Chenthamarakshan, Jerret Ross, and Brian BelgodereAccelerating discovery for societal and economic impact
ExplainerJed Pitera, Mathias Steiner, Daniel P. Sanders, Young-Hye Na, Maxwell Giammona, Kristin Schmidt, and Tim Erdmann- See more of our work on Materials Discovery
Publications
MDLab: AI frameworks for Carbon Capture and Battery Materials
- Bruce Elmegreen
- Hendrik Hamann
- et al.
- 2025
- Frontiers in Environmental Science
An open-source family of large encoder-decoder foundation models for chemistry
- 2025
- Communications Chemistry
Multi-View Mixture-of-Experts for predicting molecular properties using SMILES, SELFIES, and graph-based representations
- 2025
- Machine Learning: Science and Tech.
A Mamba-Based Foundation Model for Materials
- 2025
- NPJ AI
Novel Advanced Low-k Dielectric for 2 nm and Beyond Cu and Post Cu Dual Damascene BEOL Interconnect Technologies
- Son Nguyen
- Huai Huang
- et al.
- 2025
- VLSI Technology and Circuits 2025
Fast And Accurate Machine Learning Prediction of Back-End-Of-Line Thermal Resistances in Backside Power Delivery and Chiplet Architectures
- Prabudhya Roy Chowdhury
- Aakrati Jain
- et al.
- 2025
- ECTC 2025
Featured work
Project Photoresist
We used our accelerated discovery process to identify and synthesize a novel photoacid generator in less than a year — far quicker than it usually takes.