Latest News

• 10/01/2024: Recent Preprint "Fully Hyperbolic Neural Networks: A Novel Approach to Studying Aging Trajectories" can be downloaded from BioXiv.
• 5/11/2024: "Hyperbolic graph embedding of MEG brain networks to study brain alterations in individuals with subjective cognitive decline" is accepted by IEEE Journal of Biomedical and Health Informatics (JBHI) [Github Code].
• 3/14/2024: "A framework of computer vision-enhanced microfluidic approach for automated assessment of the transient sickling kinetics in sickle red blood cells." is accepted by Frontiers in Physics.
• 12/22/2023: "TransformerG2G: Adaptive Time-Stepping for Learning Temporal Graph Embeddings Using Transformers" is accepted by Neural Networks [Github Code].
• 9/21/2023: "Norm-Based Generalization Bounds for Compositionally Sparse Neural Networks" appears in NeurIPS2023 (New Orleans, LA).
• 3/8/2023: "Dynamics in Deep Classifiers Trained with the Square Loss: Normalization, Low Rank, Neural Collapse, and Generalization Bounds" is published in the Science Partner Journal Research (MIT News)
• 5/20/2022: "DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs" is accepted by IEEE TNNLS. [Github Code]

Media