Multi-View Mixture-of-Experts for predicting molecular properties using SMILES, SELFIES, and graph-based representations
- 2025
- Machine Learning: Science and Tech.
Indra Priyadarsini is a Research Scientist at IBM Research – Tokyo, where she focuses on developing models and algorithms for foundation models in materials discovery. She earned her B.E. in Electronics and Communication Engineering from PES Institute of Technology, Bangalore, India, in 2016, followed by an M.E. and Ph.D. from Shizuoka University, Japan, in 2019 and 2022, respectively. Her doctoral research centered on optimization algorithms and deep learning. She is currently actively involved in advanced research related to multimodal foundation models and their application to accelerated scientific discovery. She has contributed to open-source frameworks in AI for science and has been recognized with the IPSJ Industrial Achievement Award (2024) for her impactful work in AI-based materials research.