Related papers: Source Matching and Rewriting

Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should…

Schema matching is a crucial task in data integration, involving the alignment of a source schema with a target schema to establish correspondence between their elements. This task is challenging due to textual and semantic heterogeneity,…

High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers'…

Sound source localization task aims to identify the locations of sound-emitting objects by leveraging correlations between audio and visual modalities. Most existing SSL methods rely on contrastive learning-based feature matching, but lack…

Automatic Differentiation (AD) has become a dominant technique in ML. AD frameworks have first been implemented for imperative languages using tapes. Meanwhile, functional implementations of AD have been developed, often based on dual…

This work revisits and extends synthetic query generation pipelines for Neural Information Retrieval (NIR) by leveraging the InPars Toolkit, a reproducible, end-to-end framework for generating training data using large language models…

Domain-specific languages (DSLs) are integral to various software workflows. Such languages offer domain-specific optimizations and abstractions that improve code readability and maintainability. However, leveraging these languages requires…

As of today the programming language of the vast majority of the published source code is manually specified or programmatically assigned based on the sole file extension. In this paper we show that the source code programming language…

Generating performant executables from high level languages is critical to software performance across a wide range of domains. Modern compilers perform this task by passing code through a series of well-studied optimizations at…

BACKGROUND: Modern distributed systems replicate data across multiple execution sites. Business requirements and resource constraints often necessitate mixing different languages across replica sites. To facilitate the management of…

Large Language Models (LLMs) have shown strong performance in automated source-to-target code translation through pretraining on extensive code corpora. However, mainstream LLM-based code translation methods suffer from two critical…

In this paper, we leverage low-level compiler intermediate representations (IR) to improve code translation. Traditional transpilers rely on syntactic information and handcrafted rules, which limits their applicability and produces…

Large language models (LLMs) fine-tuned for text-retrieval have demonstrated state-of-the-art results across several information retrieval (IR) benchmarks. However, supervised training for improving these models requires numerous labeled…

This article is primarily meant to present an early case study on using MLIR, a new compiler intermediate representation infrastructure, for high-performance code generation. Aspects of MLIR covered in particular include memrefs, the affine…

Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures,…

This report presents some early results on code generation targeting tensor cores on NVIDIA GPUs using the MLIR compiler infrastructure. The state-of-the-art in high-performance deep learning today is primarily driven by manually optimized…

Speech LLM-based ASR often struggles with named entities and long-tail words due to strong internal language-model priors. Retrieval-augmented biasing can help, but its effectiveness depends on accurate hotword localization in…

Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a compositional query, consisting of a reference image and a modifying text-without relying on annotated training data. Existing approaches often generate a…

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…

Copy-paste-modify is a widespread and pragmatic practice in software development, where developers adapt reused code snippets, sourced from platforms such as Stack Overflow, GitHub, or LLM outputs, into their local codebase. A critical yet…