Matteo Manica

TL;DR: BLOOM as discussed by the authors is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total).

TL;DR: A hybrid system that combines a von Neumann machine with a computational memory unit can offer both the high precision of digital computing and the energy/areal efficiency of in-memory computing, which is illustrated by accurately solving a system of 5,000 equations using 998,752 phase-change memory devices.

TL;DR: In this article, a mixed precision in-memory computing (MIMO) system is proposed, which combines a von Neumann machine with a computational memory unit. But it does not address the limitations arising from device variability and nonideal device characteristics.

TL;DR: In this article, a multimodal attention-based convolutional encoder was proposed for interpretable prediction of anticancer compound sensitivity using protein-protein interaction networks (PIPI).

TL;DR: A deep learning based generative modeling framework to design drug candidates specific to a given target protein sequence with high off-target selectivity is presented, and an in silico screening process that accounts for toxicity is augmented to lower the failure rate of the generated drug candidates in later stages of the drug development pipeline.