Related papers: Deep Lake: a Lakehouse for Deep Learning

Pipelining between data loading and computation is a critical tensor program optimization for GPUs. In order to unleash the high performance of latest GPUs, we must perform a synergetic optimization of multi-stage pipelining across the…

Active learning is perhaps most naturally posed as an online learning problem. However, prior active learning approaches with deep neural networks assume offline access to the entire dataset ahead of time. This paper proposes VeSSAL, a new…

Table extraction from PDF and image documents is a ubiquitous task in the real-world. Perfect extraction quality is difficult to achieve with one single out-of-box model due to (1) the wide variety of table styles, (2) the lack of training…

The variety of data in data lakes presents significant challenges for data analytics, as data scientists must simultaneously analyze multi-modal data, including structured, semi-structured, and unstructured data. While Large Language Models…

Scanning and filtering over multi-dimensional tables are key operations in modern analytical database engines. To optimize the performance of these operations, databases often create clustered indexes over a single dimension or…

The amazing advances being made in the fields of machine and deep learning are a highlight of the Big Data era for both enterprise and research communities. Modern applications require resources beyond a single node's ability to provide.…

Large Language Models (LLMs) have shown remarkable proficiency in natural language understanding (NLU), opening doors for innovative applications. We introduce StreamLink - an LLM-driven distributed data system designed to improve the…

Deep convolutional neural networks (CNNs) have achieved remarkable success in various fields. However, training an excellent CNN is practically a trial-and-error process that consumes a tremendous amount of time and computer resources. To…

With the success of deep learning techniques in a broad range of application domains, many deep learning software frameworks have been developed and are being updated frequently to adapt to new hardware features and software libraries,…

DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic systems focus on a particular paradigm and semantics, DeepLog serves as a universal…

Through a natural language interface (NLI) for exploratory visual analysis, users can directly "ask" analytical questions about the given tabular data. This process greatly improves user experience and lowers the technical barriers of data…

The diversity and quantity of data warehouses, gathering data from distributed devices such as mobile devices, can enhance the success and robustness of machine learning algorithms. Federated learning enables distributed participants to…

Although deep learning models perform remarkably well across a range of tasks such as language translation and object recognition, it remains unclear what high-level logic, if any, they follow. Understanding this logic may lead to more…

Machine-learning from a disparate set of tables, a data lake, requires assembling features by merging and aggregating tables. Data discovery can extend autoML to data tables by automating these steps. We present an in-depth analysis of such…

A data lake is a repository of data with potential for future analysis. However, both discovering what data is in a data lake and exploring related data sets can take significant effort, as a data lake can contain an intimidating amount of…

River is a machine learning library for dynamic data streams and continual learning. It provides multiple state-of-the-art learning methods, data generators/transformers, performance metrics and evaluators for different stream learning…

The recent successes of deep learning have led to a wave of interest from non-experts. Gaining an understanding of this technology, however, is difficult. While the theory is important, it is also helpful for novices to develop an intuitive…

Distributed acoustic sensing (DAS) systems generate continuous, ultra-high-channel-count data streams at rates that exceed the capabilities of conventional batch-oriented analysis frameworks. As a result, essential tasks such as interactive…

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either…

As modern data pipelines continue to collect, produce, and store a variety of data formats, extracting and combining value from traditional and context-rich sources such as strings, text, video, audio, and logs becomes a manual process…