Related papers: VoxCap: FFT-Accelerated and Tucker-Enhanced Capaci…

Incremental scene reconstruction is essential to the navigation in robotics. Most of the conventional methods typically make use of either TSDF (truncated signed distance functions) volume or neural networks to implicitly represent the…

While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds. Existing methods attempt to overcome this issue by…

Vision Transformers (ViTs) have achieved remarkable success across various vision tasks, yet their deployment is often hindered by prohibitive computational costs. While structured weight pruning and token compression have emerged as…

X-ray tomographic reconstruction typically uses voxel basis functions to represent volumetric images. Due to the structure in voxel basis representations, efficient ray-tracing methods exist allowing fast, GPU accelerated implementations.…

In recent years, advancements in representation learning and language models have propelled Automated Captioning (AC) to new heights, enabling the generation of human-level descriptions. Leveraging these advancements, we propose AVCap, an…

Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world. Memory-based methods like LUMEN pre-compute token representations for retrieved passages to drastically speed up…

Tucker decomposition has been widely used in a variety of applications to obtain latent factors of tensor data. In these applications, a common need is to compute Tucker decomposition for a given time range. Furthermore, real-world tensor…

In this study, we propose a new method for constrained combinatorial optimization using variational quantum circuits. Quantum computers are considered to have the potential to solve large combinatorial optimization problems faster than…

Capsule Network (CapsNet) has shown significant improvement in understanding the variation in images along with better generalization ability compared to traditional Convolutional Neural Network (CNN). CapsNet preserves spatial relationship…

Fast Fourier transform (FFT) based methods have turned out to be an effective computational approach for numerical homogenisation. In particular, Fourier-Galerkin methods are computational methods for partial differential equations that are…

In this work, we present a dense tracking and mapping system named Vox-Fusion, which seamlessly fuses neural implicit representations with traditional volumetric fusion methods. Our approach is inspired by the recently developed implicit…

Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory…

We present an efficient and accurate immersed boundary (IB) finite element (FE) method for internal flow problems with complex geometries (e.g., blood flow in the vascular system). In this study, we use a voxelized flow domain (discretized…

Existing face super-resolution (SR) methods mainly assume the input image to be noise-free. Their performance degrades drastically when applied to real-world scenarios where the input image is always contaminated by noise. In this paper, we…

In this work, we develop an optimization framework for problems whose solutions are well-approximated by Hierarchical Tucker (HT) tensors, an efficient structured tensor format based on recursive subspace factorizations. By exploiting the…

Vision Transformers (ViTs) leverage the transformer architecture to effectively capture global context, demonstrating strong performance in computer vision tasks. A major challenge in ViT hardware acceleration is that the model family…

Modern microprocessors extend their instruction set architecture (ISA) with Single Instruction, Multiple Data (SIMD) operations to improve performance. The Intel Advanced Vector Extensions (AVX) enhance the x86 ISA and are widely supported…

VPIC is a general purpose Particle-in-Cell simulation code for modeling plasma phenomena such as magnetic reconnection, fusion, solar weather, and laser-plasma interaction in three dimensions using large numbers of particles. VPIC's…

We investigate the compilation of general multilinear variational forms over affines simplices and prove a representation theorem for the representation of the element tensor (element stiffness matrix) as the contraction of a constant…

This paper describes the implementation and performance of adiabatic absorbing layers in an FFT-accelerated volume integral equation (VIE) method for simulating truncated nanophotonics structures. At the truncation sites, we place absorbing…