Related papers: Sliding Window Sum Algorithms for Deep Neural Netw…
Recent advances in Schramm-Loewner evolution have driven increasing interest in non-standard Loewner flows. In this work, we propose a novel splitting algorithm to simulate random Loewner curves with rigorous convergence analysis in…
Graph Neural Networks (GNN) have demonstrated state-of-the-art performance in numerous scientific and high-performance computing (HPC) applications. Recent work suggests that "souping" (combining) individually trained GNNs into a single…
Topological defects unavoidably form at symmetry breaking phase transitions in the early Universe. To probe the parameter space of theoretical models and set tighter experimental constraints (exploiting the recent advances in astrophysical…
Convolution is the most time-consuming operation in deep neural network operations, so its performance is critical to the overall performance of the neural network. The commonly used methods for convolution on GPU include the general matrix…
Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks. Advances on CNN architectures have focused mainly on designing convolutional blocks of the feature extractors, but less on…
Previous VoIP steganalysis methods face great challenges in detecting speech signals at low embedding rates, and they are also generally difficult to perform real-time detection, making them hard to truly maintain cyberspace security. To…
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…
Sliding super point is a special host defined under sliding time window with which there are huge other hosts contact. It plays important roles in network security and management. But how to detect them in real time from nowadays high-speed…
Convolution is a broadly useful operation with applications including signal processing, machine learning, probability, optics, polynomial multiplication, and efficient parsing. Usually, however, this operation is understood and implemented…
Geometry processing presents a variety of difficult numerical problems, each seeming to require its own tailored solution. This breadth is largely due to the expansive list of geometric primitives, e.g., splines, triangles, and hexahedra,…
Convolution is the core operation for many deep neural networks. The Winograd convolution algorithms have been shown to accelerate the widely-used small convolution sizes. Quantized neural networks can effectively reduce model sizes and…
An emerging generative artificial intelligence (AI) based on neural networks starts to grow in popularity with a revolutionizing capability of creating new and original content. As giant generative models with millions to billions of…
Detecting and visualizing what are the most relevant changes in an evolving network is an open challenge in several domains. We present a fast algorithm that filters subsets of the strongest nodes and edges representing an evolving weighted…
Automatic analysis of highly crowded people has attracted extensive attention from computer vision research. Previous approaches for crowd counting have already achieved promising performance across various benchmarks. However, to deal with…
There has been a growing effort in studying the distributed optimization problem over a network. The objective is to optimize a global function formed by a sum of local functions, using only local computation and communication. Literature…
The generalized winding number (GWN) is a scalar field that supports robust containment queries on curved geometry, including non-watertight, overlapping, and nested boundary representations. While queries can be easily parallelized over…
Over the past decade, deep learning research has been accelerated by increasingly powerful hardware, which facilitated rapid growth in the model complexity and the amount of data ingested. This is becoming unsustainable and therefore…
Long interaction histories are central to modern recommender systems, yet training with long sequences is often dismissed as impractical under realistic memory and latency budgets. This work demonstrates that it is not only practical but…
Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for…
Deep neural networks represent the gold standard for image classification. However, they usually need large amounts of data to reach superior performance. In this work, we focus on image classification problems with a few labeled examples…