Most distributed machine learning systems nowadays, including TensorFlow and CNTK, are
built in a centralized fashion. One bottleneck of centralized algorithms lies on high …

The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based
multilayer perceptron (MLP) with shallow structure are well-recognized neural …

While training a machine learning model using multiple workers, each of which collects data
from its own data source, it would be useful when the data collected from different workers …

The high computational and memory requirements of large language model (LLM) inference
make it feasible only with multiple high-end accelerators. Motivated by the emerging …

Semantic segmentation of remotely sensed urban scene images is required in a wide range
of practical applications, such as land cover mapping, urban change detection, …

Cardiac hypertrophy is a common response to pressure overload and is associated with
increased mortality. Mechanical stress in the heart can result in the integrin-mediated activation …

Language models (LMs) are becoming the foundation for almost all major language
technologies, but their capabilities, limitations, and risks are not well understood. We present …

Cerebral organoids, three-dimensional cultures that model organogenesis, provide a new
platform to investigate human brain development. High cost, variability, and tissue …

As artificial intelligence (AI) transitions from research to deployment, creating the appropriate
datasets and data pipelines to develop and evaluate AI models is increasingly the biggest …

Large language models (LLMs) with hundreds of billions of parameters have sparked a new
wave of exciting AI applications. However, they are computationally expensive at inference …