A Multi-View Mixture-of-Experts based on Language and Graphs for Molecular Properties Prediction
- 2024
- ICML 2024
Eduardo Soares is a senior researcher at IBM Research Brazil, where he works in the AI-Assisted Decision-Making group. He received his PhD in Computer Science from Lancaster University (UK) in 2022, during which time he was sponsored by Ford Motors Co. Greenfield labs in Silicon Valley to develop new Explainable Deep Learning models for autonomous cars. He was awarded Best Doctoral Thesis by the International Neural Network Society (INNS). With over 50 scientific articles published in peer-reviewed conferences and journals (which have received over 1500 citations), Eduardo is an accomplished researcher in his field. He was awarded Best Paper Author during the World Conference on Computational Intelligence in 2018. He is also part of the editorial board of the Evolving Systems journal and has served as a reviewer for prestigious conferences and journals such as IEEE Transactions on Fuzzy Systems, IEEE Transactions on Cybernetics Systems, and Neurips. Eduardo's current research interests include Foundation Models for Science, Explainability of AI, Uncertainty Estimation.