Domain-specific hardware is becoming a promising topic in the backdrop of improvement
slow down for general-purpose processors due to the foreseeable end of Moore's Law …

With the wide deployments of heterogeneous networks, huge amounts of data with
characteristics of high volume, high variety, high velocity, and high veracity are generated …

Foundation models, now powering most of the exciting applications in deep learning, are
almost universally based on the Transformer architecture and its core attention module …

Transformers have revolutionized almost all natural language processing (NLP) tasks but
suffer from memory and computational complexity that scales quadratically with sequence …

There are currently no effective biomarkers for diagnosing Parkinson's disease (PD) or
tracking its progression. Here, we developed an artificial intelligence (AI) model to detect PD …

Models using structured state space sequence (S4) layers have achieved state-of-the-art
performance on long-range sequence modeling tasks. An S4 layer combines linear state …

Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations
(NDEs) are popular families of deep learning models for time-series data, each with unique …

Machine learning (ML) systems often exhibit unexpectedly poor behavior when they are
deployed in real-world domains. We identify underspecification in ML pipelines as a key …

Transformers have surpassed RNNs in popularity due to their superior abilities in parallel
training and long-term dependency modeling. Recently, there has been a renewed interest …

Real-world data often exhibit imbalanced distributions, where certain target values have
significantly fewer observations. Existing techniques for dealing with imbalanced data focus …