Related papers: Threaded Code Generation with a Meta-Tracing JIT C…

Large language models (LLMs) achieve strong performance on code generation, but the mechanisms by which Chain-of-Thought (CoT) prompting helps remain unclear. We present a systematic empirical and information-theoretic study of CoT…

Manual engineering of high-performance implementations typically consumes many resources and requires in-depth knowledge of the hardware. Compilers try to address these problems; however, they are limited by design in what they can do. To…

Representation learning of source code is essential for applying machine learning to software engineering tasks. Learning code representation from a multilingual source code dataset has been shown to be more effective than learning from…

Dynamic Translation (DT) is a sophisticated technique that allows the implementation of high-performance emulators and high-level-language virtual machines. In this technique, the guest code is compiled dynamically at runtime. Consequently,…

This work presents MLIR, a novel approach to building reusable and extensible compiler infrastructure. MLIR aims to address software fragmentation, improve compilation for heterogeneous hardware, significantly reduce the cost of building…

We propose an iterative programmatic planning (IPP) framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code using large language models (LLMs). Instead of relying on traditional search or…

Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this…

Code generation is increasingly critical for real-world applications. Still, diffusion-based large language models continue to struggle with this demand. Unlike free-form text, code requires syntactic precision; even minor structural…

In many common scenarios, programmers need to implement functionality that is already provided by some third party library. This paper presents a tool called Hunter that facilitates code reuse by finding relevant methods in large code bases…

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…

Large-scale, high-quality data is essential for advancing the reasoning capabilities of large language models (LLMs). As publicly available Internet data becomes increasingly scarce, synthetic data has emerged as a crucial research…

Python's dynamic typing system offers flexibility and expressiveness but can lead to type-related errors, prompting the need for automated type inference to enhance type hinting. While existing learning-based approaches show promising…

This article presents a complete scheme for the development of Critical Embedded Systems with Multiple Real-Time Constraints. The system is programmed with a language that extends the synchronous approach with high-level real-time…

Gradual typing combines static and dynamic typing in the same program. One would hope that the performance in a gradually typed language would range between that of a dynamically typed language and a statically typed language. Existing…

The rapid development of large language models (LLMs), such as ChatGPT, has revolutionized the efficiency of creating programming tutorials. LLMs can be instructed with text prompts to generate comprehensive text descriptions of code…

Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but inherently sequential decoding leads to substantial latency, especially on complex tasks. Recent work on adaptive…

Pure Lucid programs are concurrent with very fine granularity. Sequential Threads (STs) are functions introduced to enlarge the grain size; they are passed from server to workers by Communication Procedures (CPs) in the General Intensional…

Recent research in information extraction (IE) focuses on utilizing code-style inputs to enhance structured output generation. The intuition behind this is that the programming languages (PLs) inherently exhibit greater structural…

The ever-increasing need for fast data processing demands new methods for efficient query execution. Just-in-time query compilation techniques have been demonstrated to improve performance in a set of analytical tasks significantly. In this…

We present SPDL (Scalable and Performant Data Loading), an open-source, framework-agnostic library designed for efficiently loading array data to GPU. Data loading is often a bottleneck in AI applications, and is challenging to optimize…