Michael Bronstein

Simple logit averaging during training, not complex attention mechanisms, unlocks state-of-the-art performance in non-invasive speech BCIs, outperforming prior winners by a significant margin.

A single weight-space encoder now masters 100 transformer architectures, outperforming specialized models and handling unseen, larger networks with less memory.

Boost macrocycle generation rates from 1% to 99% by guiding diffusion models with persistent homology, opening new avenues for drug discovery.