Related papers: Divide-and-Conquer Meets Consensus: Unleashing the…

The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages, enabling analysis in scenarios where source code is unavailable. This task supports various reverse…

Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications. However, when handling tasks involving repetitive sub-tasks and/or deceptive contents, such as…

Code review is a fundamental process in software development that plays a pivotal role in ensuring code quality and reducing the likelihood of errors and bugs. However, code review can be complex, subjective, and time-consuming. Quality…

This paper addresses the gradient coding and coded matrix multiplication problems in distributed optimization and coded computing. We present a numerically stable binary coding method which overcomes the drawbacks of the \textit{Fractional…

Existing large language model-based code generation pipelines typically use beam search or sampling algorithms during the decoding process. Although the programs they generate achieve high token-matching-based scores, they often fail to…

Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting…

Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed,…

Code generation has shown great promise in assisting software development. A fundamental yet underexplored question is how the choice of code representation affects model performance. While existing studies employ various representations,…

Distributed computation is a framework used to break down a complex computational task into smaller tasks and distributing them among computational nodes. Erasure correction codes have recently been introduced and have become a popular…

Decomposable tasks are complex and comprise of a hierarchy of sub-tasks. Spoken intent prediction, for example, combines automatic speech recognition and natural language understanding. Existing benchmarks, however, typically hold out…

Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific…

Automated code generation is gaining significant importance in intelligent computer programming and system deployment. However, current approaches often face challenges in computational efficiency and lack robust mechanisms for code parsing…

Code Large Language Models (CodeLLMs) have ushered in a new era in code generation advancements. However, selecting the best code solutions from all possible CodeLLM outputs remains a challenge. Previous methods often overlooked the…

We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision. This…

Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored.…

In this paper, we investigate the problem of multi-user linearly decomposable function computation, where $N$ servers help compute functions for $K$ users, and where each such function can be expressed as a linear combination of $L$ basis…

Test-time scaling has emerged as a promising approach for improving code generation by exploring large solution spaces at inference time. However, existing methods often rely on public test cases that are unavailable in practice, or require…

Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce ConceptCoder, a fine-tuning method that…

In the context of big data analysis, the divide-and-conquer methodology refers to a multiple-step process: first splitting a data set into several smaller ones; then analyzing each set separately; finally combining results from each…

The "Divide and Concur'' (DC) algorithm, recently introduced by Gravel and Elser, can be considered a competitor to the belief propagation (BP) algorithm, in that both algorithms can be applied to a wide variety of constraint satisfaction,…