相关论文: A Complex Java Code Generator for ACL2 Based on a …

We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…

Large repositories of source code for research tend to limit their utility to static analysis of the code, as they give no guarantees on whether the projects are compilable, much less runnable in any way. The immediate consequence of the…

This tool demonstration presents a research toolkit for a language model of Java source code. The target audience includes researchers studying problems at the granularity level of subroutines, statements, or variables in Java. In contrast…

Software comprehension can be extremely time-consuming due to the ever-growing size of codebases. Consequently, there is an increasing need to accelerate the code comprehension process to facilitate maintenance and reduce associated costs.…

The rapid advancement of code large language models (LLMs) has sparked significant research interest in systematically evaluating their code generation capabilities, yet existing benchmarks predominantly assess models at a single structural…

Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating high-quality and reliable code remains a formidable task because of LLMs' lack of…

This is a companion draft to paper 'Software Clustering: Unifying Syntactic and Semantic Features', in proceedings of the 19th Working Conference on Reverse Engineering (WCRE 2012). It discusses the clustering process in detail, which…

Generating code via a LLM (rather than writing code from scratch), has exploded in popularity. However, the security implications of LLM-generated code are still unknown. We performed a study that compared the security and quality of…

Grammar convergence is a method that helps discovering relationships between different grammars of the same language or different language versions. The key element of the method is the operational, transformation-based representation of…

In recent years, heterogeneous computing has emerged as the vital way to increase computers? performance and energy efficiency by combining diverse hardware devices, such as Graphics Processing Units (GPUs) and Field Programmable Gate…

Behavioral synthesis involves compiling an Electronic System-Level (ESL) design into its Register-Transfer Level (RTL) implementation. Loop pipelining is one of the most critical and complex transformations employed in behavioral synthesis.…

The Abstract Syntax Description Language (ASDL) is a language for specifying the tree data structures often found in compiler intermediate representations. The ASDL generator reads an ASDL specification and generates code to construct,…

This paper describes an ACL2 interpreter for "netlists" describing quantum circuits. Several quantum gates are implemented, including the Hadamard gate H, which rotates vectors by 45 degrees, necessitating the use of irrational numbers, at…

We address the problems of constructing quantum convolutional codes (QCCs) and of encoding them. The first construction is a CSS-type construction which allows us to find QCCs of rate 2/4. The second construction yields a quantum…

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

Large language models (LLMs) are increasingly used in software development, generating code that ranges from short snippets to substantial project components. As AI-generated code becomes more common in real-world repositories, it is…

Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…

Automatic and efficient verification of multiplier designs, especially through a provably correct method, is a difficult problem. We show how to utilize a theorem prover, ACL2, to implement an efficient rewriting algorithm for multiplier…

In this study, we assess the efficacy of employing the ChatGPT language model to generate solutions for coding exercises within an undergraduate Java programming course. ChatGPT, a large-scale, deep learning-driven natural language…

The integration of large language models (LLMs) into electronic design automation (EDA) has significantly advanced the field, offering transformative benefits, particularly in register transfer level (RTL) code generation and understanding.…