相关论文: Thistle: A Vector Database in Rust

Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented generation (RAG) are primarily designed for unstructured text and do not account for…

Multimodal data has become a crucial element in the realm of big data analytics, driving advancements in data exploration, data mining, and empowering artificial intelligence applications. To support high-quality retrieval for these…

Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic layouts and long horizons. Humans, by contrast, exploit…

Software vulnerabilities exist in open-source software (OSS), and the developers who discover these vulnerabilities may submit issue reports (IRs) to describe their details. Security practitioners need to spend a lot of time manually…

While table understanding increasingly relies on pixel-only settings, current benchmarks predominantly use synthetic renderings that lack the complexity and visual diversity of real-world tables. Additionally, existing visual table…

This paper explores how design patterns could be revisited in the era of mainstream functional programming languages. I discuss the kinds of knowledge that ought to be represented as functional design patterns: architectural concepts that…

Graph structured data on the web is now massive as well as diverse, ranging from social networks, web graphs to knowledge-bases. Effectively querying this graph structured data is non-trivial and has led to research in a variety of…

Large Language Models (LLMs) are widely used for downstream tasks such as tabular classification, where ensuring fairness in their outputs is critical for inclusivity, equal representation, and responsible AI deployment. This study…

Table foundation models bring high hopes to data science: pre-trained on tabular data to embark knowledge or priors, they should facilitate downstream tasks on tables. One specific challenge is that of data semantics: numerical entries take…

Although wide-scale integration of cloud services with myriad applications increases quality of services (QoS) for enterprise users, verifying the existence and manipulation of stored cloud information remains an open research problem.…

There is growing interest in deploying ML inference and knowledge retrieval as services that could support both interactive queries by end users and more demanding request flows that arise from AIs integrated into a end-user applications…

This paper addresses the critical need for high-quality malware datasets that support advanced analysis techniques, particularly machine learning and agentic AI frameworks. Existing datasets often lack diversity, comprehensive labelling,…

Organizations are increasingly focused on leveraging data from their processes to gain insights and drive decision-making. However, converting this data into actionable knowledge remains a difficult and time-consuming task. There is often a…

Rust is an emerging programing language that aims at preventing memory-safety bugs without sacrificing much efficiency. The claimed property is very attractive to developers, and many projects start using the language. However, can Rust…

The increasing proliferation of IoT devices and AI applications has created a demand for scalable and efficient computing solutions, particularly for applications requiring real-time processing. The compute continuum integrates edge and…

The Large Language Model (LLM) has gained significant popularity and is extensively utilized across various domains. Most LLM deployments occur within cloud data centers, where they encounter substantial response delays and incur high…

Transfer learning on tabular data is challenging due to disparate feature spaces across domains, in contrast to the homogeneous structures of image and text. Large language models (LLMs) offer a knowledge base to improve the limited…

In this paper, we enhance the machine-readable representation of the ATT&CK Groups knowledge base provided by MITRE in STIX 2.1 format to make available and queryable additional types of contextual information. Such information includes the…

As data retrieval demands become increasingly complex, traditional search methods often fall short in addressing nuanced and conceptual queries. Vector similarity search has emerged as a promising technique for finding semantically similar…

With the rapid advancement of Large Language Models (LLMs), there is an increasing need for challenging benchmarks to evaluate their capabilities in handling complex tabular data. However, existing benchmarks are either based on outdated…