4 papers
MatBind: A Shared Embedding Space for Multimodal Materials Characterization
Le Yang, Anoop K. Chandran, Jona Ãstreicher +8
Fully characterizing a crystalline material requires integrating heterogeneous data sources -- atomic structures, diffraction patterns, electronic density of states, and natural la…
General-Purpose Models for the Chemical Sciences: LLMs and Beyond
Nawaf Alampara, Anagha Aneesh, Martiño RÃos-GarcÃa +6
Data-driven techniques have a large potential to transform and accelerate the chemical sciences. However, chemical sciences also pose the unique challenge of very diverse, small, f…
ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models
Adrian Mirza, Nawaf Alampara, Martiño RÃos-GarcÃa +12
Foundation models have shown remarkable success across scientific domains, yet their impact in chemistry remains limited due to the absence of diverse, large-scale, high-quality da…
Are large language models superhuman chemists?
Adrian Mirza, Nawaf Alampara, Sreekanth Kunchapu +32
Large language models (LLMs) have gained widespread interest due to their ability to process human language and perform tasks on which they have not been explicitly trained. Howeve…