Luca Benini

STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU

Victor J. B. Jung, Gagandeep Singh, Joseph Melber, et al.

LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling

Danaé Broustail, Anna Tegon, Thorir Mar Ingolfsson, et al.

LuMamba is a new AI model designed to analyze brain activity data (EEG) more efficiently and flexibly than previous approaches. It solves two key problems: it works with different numbers and arrangements of brain sensors, and it processes information much faster (377× fewer computations) than existing models by using a modern architecture called Mamba instead of Transformers. Trained on over 21,000 hours of unlabeled EEG data, the model achieves state-of-the-art results on medical tasks like detecting Alzheimer's disease while being compact enough to run practically.