Artificial Intelligence (AI) is making a profound impact in almost every domain. A vital enabler
of its great success is the availability of abundant and high-quality data for building machine …

As the model size grows rapidly, fine-tuning the large pre-trained language model has
become increasingly difficult due to its extensive memory usage. Previous works usually …

The edge computing paradigm for Internet-of-Things brings computing closer to data
sources, such as environmental sensors and cameras, using connected smart devices. Over …

Activation compressed training provides a solution towards reducing the memory cost of
training deep neural networks (DNNs). However, state-of-the-art work combines a search of …

Action recognition is an important task for video understanding with broad applications.
However, developing an effective action recognition solution often requires extensive …

Object detection is the foundation of various critical computer-vision tasks such as
segmentation, object tracking, and event detection, which can be deployed on pervasive …

We present an end-end system for time series anomaly detection specifically aimed at
detecting fraudulent transactions in bank transaction datasets. The goal of anomaly …

Deep reinforcement learning has recently achieved remarkable success in various domains,
ranging from games [10, 11, 12], to real-world applications such as neural architecture …

In this work, we propose a novel backbone search method for object detection for
applications in intrusion warning systems. The goal is to find a compact model for use in …

Deep reinforcement learning (deep RL) has recently achieved remarkable success in
various domains, from simulated games to real-world applications. However, deep RL …