Related papers: Blockbuster, Part 1: Block-level AI Operator Fusio…

Cluster algorithms are developed for simulating quantum spin systems like the one- and two-dimensional Heisenberg ferro- and anti-ferromagnets. The corresponding two- and three-dimensional classical spin models with four-spin couplings are…

Cluster algorithms are developed for simulating quantum spin systems like the one- and two-dimensional Heisenberg ferro- and anti-ferromagnets. The corresponding two- and three-dimensional classical spin models with four-spin couplings are…

Deep neural network (DNN) architectures, such as convolutional neural networks (CNN), involve heavy computation and require hardware, such as CPU, GPU, and AI accelerators, to provide the massive computing power. With the many varieties of…

Graphical models use graphs to compactly capture stochastic dependencies amongst a collection of random variables. Inference over graphical models corresponds to finding marginal probability distributions given joint probability…

Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI. Conventional methods successfully enable convolutional neural…

Most deep architectures for image classification--even those that are trained to classify a large number of diverse categories--learn shared image representations with a single model. Intuitively, however, categories that are more similar…

The rapid progression of generative AI (GenAI) technologies has heightened concerns regarding the misuse of AI-generated imagery. To address this issue, robust detection methods have emerged as particularly compelling, especially in…

In recent years, machine-learning methods have become increasingly important for the experiments at the Large Hadron Collider (LHC). They are utilised in everything from trigger systems to reconstruction and data analysis. The recent…

We bring together topological data analysis, applied category theory, and machine learning to study multiparameter hierarchical clustering. We begin by introducing a procedure for flattening multiparameter hierarchical clusterings. We…

As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data…

Block coherence of matrices plays an important role in analyzing the performance of block compressed sensing recovery algorithms (Bajwa and Mixon, 2012). In this paper, we characterize two block coherence metrics: worst-case and average…

The rapid expansion of AI inference services in the cloud necessitates a robust scalability solution to manage dynamic workloads and maintain high performance. This study proposes a comprehensive scalability optimization framework for cloud…

Open-vocabulary 3D object detection has gained significant interest due to its critical applications in autonomous driving and embodied AI. Existing detection methods, whether offline or online, typically rely on dense point cloud…

Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model…

This paper introduces a new neural structure called FusionNet, which extends existing attention approaches from three perspectives. First, it puts forward a novel concept of "history of word" to characterize attention information from the…

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

The integration of diverse clinical modalities such as medical imaging and the tabular data extracted from patients' Electronic Health Records (EHRs) is a crucial aspect of modern healthcare. Integrative analysis of multiple sources can…

We show in this work that memory intensive computations can result in severe performance problems due to off-chip memory access and CPU-GPU context switch overheads in a wide range of deep learning models. For this problem, current…

Entity Resolution, also called record linkage or deduplication, refers to the process of identifying and merging duplicate versions of the same entity into a unified representation. The standard practice is to use a Rule based or Machine…

Fast Style Transfer is a series of Neural Style Transfer algorithms that use feed-forward neural networks to render input images. Because of the high dimension of the output layer, these networks require much memory for computation.…