Related papers: Janus: Leveraging Incremental Computation for Effi…
Efficient inference of Deep Neural Networks (DNNs) is essential to making AI ubiquitous. Two important algorithmic techniques have shown promise for enabling efficient inference - sparsity and binarization. These techniques translate into…
Applications such as web search and social networking have been moving from centralized to decentralized cloud architectures to improve their scalability. MapReduce, a programming framework for processing large amounts of data using…
This paper proposes Caesar, a novel multi-leader Generalized Consensus protocol for geographically replicated sites. The main goal of Caesar is to overcome one of the major limitations of existing approaches, which is the significant…
Deep Learning (DL) components are routinely integrated into software systems that need to perform complex tasks such as image or natural language processing. The adequacy of the test data used to test such systems can be assessed by their…
Fact verification has attracted a lot of attention in the machine learning and natural language processing communities, as it is one of the key methods for detecting misinformation. Existing large-scale benchmarks for this task have focused…
Modern computing systems increasingly rely on composing heterogeneous devices to improve performance and efficiency. Programming these systems is often unproductive: algorithm implementations must be coupled to system-specific logic,…
Limited by the scarcity of training samples and annotations, weakly supervised medical image segmentation often employs data augmentation to increase data diversity, while randomly mixing volumetric blocks has demonstrated strong…
Deep Convolutional Neural Networks (CNN) provides an "end-to-end" solution for image pattern recognition with impressive performance in many areas of application including medical imaging. Most CNN models of high performance use…
Safety-critical applications like autonomous vehicles and industrial IoT are adopting semantic communication (SemCom) systems using deep neural networks to reduce bandwidth and increase transmission speed by transmitting only task-relevant…
Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial attacks, wherein, a model gets fooled by applying slight perturbations on the input. With the advent of Internet-of-Things and the necessity to enable intelligence…
Despite the large number of sophisticated deep neural network (DNN) verification algorithms, DNN verifier developers, users, and researchers still face several challenges. First, verifier developers must contend with the rapidly changing…
This work proposes a novel Energy-Aware Network Operator Search (ENOS) approach to address the energy-accuracy trade-offs of a deep neural network (DNN) accelerator. In recent years, novel inference operators have been proposed to improve…
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…
The Domain Name System (DNS) is essential for the Internet, giving a mechanism to resolve hostnames into Internet Protocol (IP) addresses. DNS is known as the world's largest distributed database that manages hostnames and Internet…
Evolutionary neural architecture search (ENAS) has recently received increasing attention by effectively finding high-quality neural architectures, which however consumes high computational cost by training the architecture encoded by each…
Despite the integration of search tools, Deep Search Agents often suffer from a misalignment between reasoning-driven queries and the underlying web indexing structures. Existing frameworks treat the search engine as a static utility,…
Modern malware poses a severe threat to cybersecurity, continually evolving in sophistication. To combat this threat, researchers and security professionals continuously explore advanced techniques for malware detection and analysis.…
Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational…
The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has significantly lowered the computational overhead for conducting scientific research in neural architecture search (NAS). Although they have been widely adopted…
The Thomas Jefferson National Accelerator Facility (Jefferson Lab) control system uses a nameserver to reduce system response time and to minimize the impact of client name resolution on front-end computers. The control system is based on…