Related papers: Chain-of-Experts (CoE): Reverse Engineering Softwa…
Robots are being applied in a vast range of fields, leading researchers and practitioners to write tasks more complex than in the past. The robot software complexity increases the difficulty of engineering the robot's software components…
The capability of accurately determining code similarity is crucial in many tasks related to software development. For example, it might be essential to identify code duplicates for performing software maintenance. This research introduces…
Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing…
Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather…
Context: Mining software repositories is a popular means to gain insights into a software project's evolution, monitor project health, support decisions and derive best practices. Tools supporting the mining process are commonly applied by…
The practice of code reuse is crucial in software development for a faster and more efficient development lifecycle. In reality, however, code reuse practices lack proper control, resulting in issues such as vulnerability propagation and…
The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive.…
As software projects progress, quality of code assumes paramount importance as it affects reliability, maintainability and security of software. For this reason, static analysis tools are used in developer workflows to flag code quality…
Research shows, that the major issue in development of quality software is precise estimation. Further this estimation depends upon the degree of intricacy inherent in the software i.e. complexity. This paper attempts to empirically…
In this paper, we propose a Collaboration of Experts (CoE) framework to pool together the expertise of multiple networks towards a common aim. Each expert is an individual network with expertise on a unique portion of the dataset, which…
The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…
Fusing heterogeneous information remains a persistent challenge in modern data analysis. While significant progress has been made, existing approaches often fail to account for the inherent heterogeneity of object patterns across different…
Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming languages (FPLs) such as Haskell, OCaml, and Scala chronically underexplored, with even…
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.…
Software redesign preserves functionality while improving quality attributes, but manual reuse of code and tests is costly and error-prone, especially in crossrepository redesigns. Focusing on static analyzers where cross-repo redesign…
Background: The state of the art in software engineering consists of a myriad of contributions and the gaps between them; it is difficult to characterize. Questions: In order to help understanding the state of the art, can we identify gaps…
The generation quality of large language models (LLMs) is often improved by utilizing inference-time sequence-level scaling methods (e.g., Chain-of-Thought). We introduce hyper-parallel scaling, a complementary framework that improves…
In software reverse engineering, decompilation is the process of recovering source code from binary files. Decompilers are used when it is necessary to understand or analyze software for which the source code is not available. Although…
To help the open-source community have a better understanding of Mixture-of-Experts (MoE) based large language models (LLMs), we train and release OpenMoE, a series of fully open-sourced and reproducible decoder-only MoE LLMs, ranging from…
This paper describes a method for the recovering of software architectures from a set of similar (but unrelated) software products in binary form. One intention is to drive refactoring into software product lines and combine architecture…