Related papers: React-ing to Grace Hopper 200: Five Open-Weights C…

Code completion is a key feature of Integrated Development Environments (IDEs), aimed at predicting the next tokens a developer is likely to write, helping them write code faster and with less effort. Modern code completion approaches are…

Despite the success of text retrieval in many NLP tasks, code retrieval remains a largely underexplored area. Most text retrieval systems are tailored for natural language queries, often neglecting the specific challenges of retrieving…

Recent advances in large language models (LLMs) have fueled growing interest in automating geospatial analysis and GIS workflows, yet their actual capabilities remain uncertain. In this work, we call for rigorous evaluation of LLMs on…

Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work, we investigate how…

Code Agent development is an extremely active research area, where a reliable performance metric is critical for tracking progress and guiding new developments. This demand is underscored by the meteoric rise in popularity of SWE-Bench.…

In the era of "Software Engineering 2.0" (SE 2.0), where intelligent agents collaborate with human engineers, Generative AI is advancing beyond code generation into Software Architecture (SA). While Large Language Models (LLMs) demonstrate…

The recently released GPT-4 Code Interpreter has demonstrated remarkable proficiency in solving challenging math problems, primarily attributed to its ability to seamlessly reason with natural language, generate code, execute code, and…

Accelerated computing is widely used in high-performance computing. Therefore, it is crucial to experiment and discover how to better utilize GPUGPUs latest generations on relevant applications. In this paper, we present results and share…

The recent advancements of Small Language Models (SLMs) have opened new possibilities for efficient code generation. SLMs offer lightweight and cost-effective alternatives to Large Language Models (LLMs), making them attractive for use in…

This study presents the first large-scale, side-by-side comparison of contemporary Large Language Models (LLMs) in the automated grading of programming assignments. Drawing on over 6,000 student submissions collected across four years of an…

We introduce MARKET-BENCH, a benchmark that evaluates large language models (LLMs) on introductory quantitative trading tasks by asking them to construct executable backtesters from natural language strategy descriptions and market…

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We…

This study presents a comprehensive empirical evaluation of six state-of-the-art large language models (LLMs) for code generation, including both general-purpose and code-specialized models. Using a dataset of 944 real-world LeetCode…

While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradigm with SmallThinker, a family of LLMs natively designed -…

Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA) approaches rely on powerful yet closed-source large language…

The legal field already uses various large language models (LLMs) in actual applications, but their quantitative performance and reasons for it are underexplored. We evaluated several open-source and proprietary LLMs -- including…

Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective…

Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…

Recent advancements in large language models (LLMs) have demonstrated significant progress in math and code reasoning capabilities. However, existing code benchmark are limited in their ability to evaluate the full spectrum of these…