Global medium-range weather forecasting is critical to decision-making across many social
and economic domains. Traditional numerical weather prediction uses increased compute …

Structural pruning enables model acceleration by removing structurally-grouped parameters
from neural networks. However, the parameter-grou** patterns vary widely across …

Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design
computer agents with intelligent capabilities such as understanding, reasoning, and learning …

Graph neural networks (GNNs) are an emerging research field. This specialized deep
neural network architecture is capable of processing graph structured data and bridges the …

Large language models (LLMs), such as GPT4 and LLaMA, are creating significant
advancements in natural language processing, due to their strong text encoding/decoding …

In many ways, graphs are the main modality of data we receive from nature. This is due to
the fact that most of the patterns we see, both in natural and artificial systems, are elegantly …

Transitioning from fossil fuels to renewable energy sources is a critical global challenge; it
demands advances—at the materials, devices and systems levels—for the efficient …

Despite the emergence of experimental methods for simultaneous measurement of multiple
omics modalities in single cells, most single-cell datasets include only one modality. A major …