相关论文: LaraDB: A Minimalist Kernel for Linear and Relatio…

The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been…

We provide a computational definition of the notions of vector space and bilinear functions. We use this result to introduce a minimal language combining higher-order computation and linear algebra. This language extends the Lambda-calculus…

With the rapid growth of large graphs, we cannot assume that graphs can still be fully loaded into memory, thus the disk-based graph operation is inevitable. In this paper, we take the shortest path discovery as an example to investigate…

Sparse linear algebra is central to many scientific programs, yet compilers fail to optimize it well. High-performance libraries are available, but adoption costs are significant. Moreover, libraries tie programs into vendor-specific…

Laplacian matrices of graphs arise in large-scale computational applications such as semi-supervised machine learning; spectral clustering of images, genetic data and web pages; transportation network flows; electrical resistor circuits;…

This technical report details a novel approach to combining reasoning and retrieval augmented generation (RAG) within a single, lean language model architecture. While existing RAG systems typically rely on large-scale models and external…

When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong…

To leverage data and computation capabilities of mobile devices, machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models, resulting in the new paradigm of edge learning. In this paper,…

Dense linear algebra libraries, such as BLAS and LAPACK, provide a relevant collection of numerical tools for many scientific and engineering applications. While there exist high performance implementations of the BLAS (and LAPACK)…

Database workloads are increasingly nesting artificial intelligence (AI) and machine learning (ML) pipelines and AI/ML model inferences with data processing, yielding hybrid SQL+AI/ML queries that mix relational operators with expensive,…

Range aggregate queries (RAQs) are an integral part of many real-world applications, where, often, fast and approximate answers for the queries are desired. Recent work has studied answering RAQs using machine learning models, where a model…

In the recent years several research efforts have focused on the concept of time granularity and its applications. A first stream of research investigated the mathematical models behind the notion of granularity and the algorithms to manage…

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless,…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

We introduce ALARB, a dataset and suite of tasks designed to evaluate the reasoning capabilities of large language models (LLMs) within the Arabic legal domain. While existing Arabic benchmarks cover some knowledge-intensive tasks such as…

Low-Rank Adaptation (LoRA) has proven effective in reducing computational costs while maintaining performance comparable to fully fine-tuned foundation models across various tasks. However, its fixed low-rank structure restricts its…

This paper introduces a method for adapting LoRA adapters in smaller-sized language models to arbitrary downstream tasks. Unlike standard mixture-of-expert architectures, our method employs a gradient-free routing function to choose a…

Retrieval-augmented generation (RAG) has evolved into a family of paradigms with distinct performance profiles and resource demands, turning paradigm selection into a multi-criteria, context-dependent decision problem. Nevertheless,…

Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) addresses these issues by grounding LLM…

AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specifically, it decouples the KV cache and attention computation from…