AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Application-specific system-on-chip (SoC) design offers the opportunity for incorporating
custom network-on-chip (NoC) architectures that are more suitable for a particular application, …

Contact-rich manipulation tasks in unstructured environments often require both haptic and
visual feedback. However, it is non-trivial to manually design a robot controller that combines …

Large, high-capacity models trained on diverse datasets have shown remarkable successes
on efficiently tackling downstream applications. In domains from NLP to Computer Vision, …

The new hydrophobic octylamine‐based polybenzoxazines (POPBOs) and flexible aliphatic
chain donating hexa‐methylene diamine‐based polybenzoxazines (PHPBOs) have been …

Robot manipulation has seen tremendous progress in recent years, with imitation learning
policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently…

We propose a neural multi-document summarization system that incorporates sentence
relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with …

It is currently challenging to analyze single-cell data consisting of many cells and samples,
and to address variations arising from batch effects and different sample preparations. For …

Safety remains a central obstacle preventing widespread use of RL in the real world: learning
new tasks in uncertain environments requires extensive exploration, but safety requires …

The endoplasmic reticulum (ER) and mitochondria communicate via contact sites known as
mitochondria-associated ER membranes or MAM. The region has emerged as the primary …