Related papers: SODA: A Semantics-Aware Optimization Framework for…
Recently, large language models (LLMs) have significantly improved the performance of text-to-SQL systems. Nevertheless, many state-of-the-art (SOTA) approaches have overlooked the critical aspect of system robustness. Our experiments…
Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…
Despite recent advances in semantic segmentation, an inevitable challenge is the performance degradation caused by the domain shift in real applications. Current dominant approach to solve this problem is unsupervised domain adaptation…
With the rapid advancement of Big Data platforms such as Hadoop, Spark, and Dataflow, many tools are being developed that are intended to provide end users with an interactive environment for large-scale data analysis (e.g., IQmulus).…
Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source domains to unlabeled target domains. When adapting to adverse scenes, existing UDA methods fail to perform well due to the lack of instructions, leading their…
The amount of data in the world is expanding rapidly. Every day, huge amounts of data are created by scientific experiments, companies, and end users' activities. These large data sets have been labeled as "Big Data", and their storage,…
Learned optimizers are a crucial component of meta-learning. Recent advancements in scalable learned optimizers have demonstrated their superior performance over hand-designed optimizers in various tasks. However, certain characteristics of…
Logs provide valuable insights into system runtime and assist in software development and maintenance. Log parsing, which converts semi-structured log data into structured log data, is often the first step in automated log analysis. Given…
Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce…
Current machine algorithms for analysis of unstructured data typically show low accuracies due to the need for human-like intelligence. Conversely, though humans are much better than machine algorithms on analyzing unstructured data, they…
Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…
The rapid growth of data in velocity, volume, value, variety, and veracity has enabled exciting new opportunities and presented big challenges for businesses of all types. Recently, there has been considerable interest in developing systems…
Most state of the art exploratory data analysis frameworks fall into one of the two extremes: they either focus on the high-performance computational, or on the interactive and open-ended aspects of the analysis. Arkouda is a framework that…
Modern distributed data processing systems struggle to balance performance, maintainability, and developer productivity when integrating machine learning at scale. These challenges intensify in large collaborative environments due to high…
Documents are central to many business systems, and include forms, reports, contracts, invoices or purchase orders. The information in documents is typically in natural language, but can be organized in various layouts and formats. There…
Robotic Mobile Fulfillment Systems (RMFS) rely on mobile robots for automated inventory transportation, coordinating order allocation and robot scheduling to enhance warehousing efficiency. However, optimizing RMFS is challenging due to…
As data volumes grow across applications, analytics of large amounts of data is becoming increasingly important. Big data processing frameworks such as Apache Hadoop, Apache AsterixDB, and Apache Spark have been built to meet this demand. A…
While modern parallel computing systems offer high performance, utilizing these powerful computing resources to the highest possible extent demands advanced knowledge of various hardware architectures and parallel programming models.…
Semantic operators have increasingly become integrated within data systems to enable processing data using Large Language Models (LLMs). Despite significant recent effort in improving these operators, their accuracy is limited due to a…
The SINTAGMA information integration system is an infrastructure for accessing several different information sources together. Besides providing a uniform interface to the information sources (databases, web services, web sites, RDF…