Eduardo Soares

Eduardo Soares is a Senior Research Scientist at IBM Research - Brazil, specialized in the design and pre-training of large multimodal foundation models for materials science. Eduardo's work integrates diverse chemical representations, including SMILES and 3D electron density grids, to advance foundational models for material property prediction and chemical language modeling. Previously, Eduardo contributed to the development of explainable AI techniques for autonomous systems and trustworthy deep learning methodologies.

Eduardo Soares earned his Ph.D. in Computer Science from Lancaster University, where his research received the Best Doctoral Dissertation Award from the International Neural Networks Society in 2022. His work has been presented at top leading conferences such as NeurIPS, ICML, and AAAI, resulting in more than 2300 citations.

Explore our work: IBM FM4M GitHub Repository