相关论文: Thistle: A Vector Database in Rust

Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. These methods, however, are orders of magnitude slower and…

Considering relational databases having powerful capabilities in handling security, user authentication, query optimization, etc., several commercial and academic frameworks reuse relational databases to store and query semi-structured data…

Existing C to Rust translation techniques fail to balance quality and scalability: transpilation-based approaches scale to large projects but produce code with poor safety, idiomaticity, and readability. In contrast, LLM-based techniques…

Vector representations of graphs and relational structures, whether hand-crafted feature vectors or learned representations, enable us to apply standard data analysis and machine learning techniques to the structures. A wide range of…

Rusty Variation (RV) is a library for session-typed communication in Rust which offers strong compile-time correctness guarantees. Programs written using RV are guaranteed to respect a specified protocol, and are guaranteed to be free from…

Verilog's design cycle is inherently labor-intensive and necessitates extensive domain expertise. Although Large Language Models (LLMs) offer a promising pathway toward automation, their limited training data and intrinsic sequential…

We propose Cognitive Databases, an approach for transparently enabling Artificial Intelligence (AI) capabilities in relational databases. A novel aspect of our design is to first view the structured data source as meaningful unstructured…

This paper addresses volume leakage (i.e., leakage of the number of records in the answer set) when processing keyword queries in encrypted key-value (KV) datasets. Volume leakage, coupled with prior knowledge about data distribution and/or…

We introduce a novel latent vector space model that jointly learns the latent representations of words, e-commerce products and a mapping between the two without the need for explicit annotations. The power of the model lies in its ability…

Existing tabular reasoning benchmarks mostly test models on small, uniform tables, underrepresenting the complexity of real-world data and giving an incomplete view of Large Language Models' (LLMs) reasoning abilities. Real tables are long,…

The continually increasing number of complex datasets each year necessitates ever improving machine learning methods for robust and accurate categorization of these data. This paper introduces Random Multimodel Deep Learning (RMDL): a new…

As ecommerce continues growing, huge investments in ML and NLP for Information Retrieval are following. While the vector space model dominated retrieval modelling in product search - even as vectorization itself greatly changed with the…

Rust is a memory-safe programming language that significantly improves software security. Existing codebases written in unsafe memory languages, such as C, must first be transpiled to Rust to take advantage of Rust's improved safety…

Online multi-object tracking (MOT) is a longstanding task for computer vision and intelligent vehicle platform. At present, the main paradigm is tracking-by-detection, and the main difficulty of this paradigm is how to associate current…

Sorted Table Search Procedures are the quintessential query-answering tool, with widespread usage that now includes also Web Applications, e.g, Search Engines (Google Chrome) and ad Bidding Systems (AppNexus). Speeding them up, at very…

Rust is a new and promising high-level system programming language. It provides both memory safety and thread safety through its novel mechanisms such as ownership, moves and borrows. Ownership system ensures that at any point there is only…

Many organizations seek to ensure that machine learning (ML) and artificial intelligence (AI) systems work as intended in production but currently do not have a cohesive methodology in place to do so. To fill this gap, we propose MLTE…

In this paper, we build a model named VuLASTE, which regards vulnerability detection as a special text classification task. To solve the vocabulary explosion problem, VuLASTE uses a byte level BPE algorithm from natural language processing.…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in…

Scientific discovery is increasingly dependent on a scientist's ability to acquire, curate, integrate, analyze, and share large and diverse collections of data. While the details vary from domain to domain, these data often consist of…