Related papers: SINDI: an Efficient Index for Approximate Maximum …

Graph-based Approximate Nearest Neighbor (ANN) search often suffers from performance degradation in high-dimensional spaces due to the Euclidean-Geodesic mismatch, where greedy routing diverges from the underlying data manifold. To address…

Sparse variable selection improves interpretability and generalization in high-dimensional learning by selecting a small subset of informative features. Recent advances in Mixed Integer Programming (MIP) have enabled solving large-scale…

Identifying the governing equations of a dynamical system is one of the most important tasks for scientific modeling. However, this procedure often requires high-quality spatio-temporal data uniformly sampled on structured grids. In this…

We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation -- multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either…

Anserini is a Lucene-based toolkit for reproducible information retrieval research in Java that has been gaining traction in the community. It provides retrieval capabilities for both "traditional" bag-of-words retrieval models such as BM25…

This paper discusses clustering and latent semantic indexing (LSI) aspects of the singular value decomposition (SVD). The purpose of this paper is twofold. The first is to give an explanation on how and why the singular vectors can be used…

The Sparse Identification of Nonlinear Dynamics (SINDy) is a method for discovering nonlinear dynamical system models from data. Quantifying uncertainty in SINDy models is essential for assessing their reliability, particularly in…

Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the…

SINDy is a method for learning system of differential equations from data by solving a sparse linear regression optimization problem [Brunton et al., 2016]. In this article, we propose an extension of the SINDy method that learns systems of…

Model inversion is a widely adopted technique in data-free learning that reconstructs synthetic inputs from a pretrained model through iterative optimization, without access to original training data. Unfortunately, its application to…

Neural models have transformed the fundamental information retrieval problem of mapping a query to a giant set of items. However, the need for efficient and low latency inference forces the community to reconsider efficient approximate…

To overcome the performance limitations in modern computing, such as the power wall, emerging computing paradigms are gaining increasing importance. Approximate computing offers a promising solution by substantially enhancing energy…

Approximate Nearest Neighbor Search with arbitrary filtering predicates (AFANNS) is essential for modern data applications, yet existing methods often incur substantial storage and computational costs. In this work, we introduce the Maximal…

Spatial data is ubiquitous. Massive amounts of data are generated every day from a plethora of sources such as billions of GPS-enabled devices (e.g., cell phones, cars, and sensors), consumer-based applications (e.g., Uber and Strava), and…

Modeling real-world spatio-temporal data is exceptionally difficult due to inherent high dimensionality, measurement noise, partial observations, and often expensive data collection procedures. In this paper, we present Sparse…

Compute-in-memory (CIM) accelerators for spiking neural networks (SNNs) are promising solutions to enable $\mu$s-level inference latency and ultra-low energy in edge vision applications. Yet, their current lack of flexibility at both the…

Indexing highly repetitive collections has become a relevant problem with the emergence of large repositories of versioned documents, among other applications. These collections may reach huge sizes, but are formed mostly of documents that…

Deep learning-based fine-grained network intrusion detection systems (NIDS) enable different attacks to be responded to in a fast and targeted manner with the help of large-scale labels. However, the cost of labeling causes insufficient…

Spiking neural networks (SNNs) are artificial neural networks based on simulated biological neurons and have attracted much attention in recent artificial intelligence technology studies. The dendrites in biological neurons have efficient…

Sparse Convolution (SC) is widely used for processing 3D point clouds that are inherently sparse. Different from dense convolution, SC preserves the sparsity of the input point cloud by only allowing outputs to specific locations. To…