相关论文: WizardMerge -- Save Us From Merging Without Any Cl…
Large Language Models (LLMs) have demonstrated significant capability in code generation, but their potential in code efficiency optimization remains underexplored. Previous LLM-based code efficiency optimization approaches exclusively…
Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the…
This paper presents an intra coding tool, named Merge mode for Template-based Intra Mode Derivation (TIMD). TIMD-Merge has been adopted in the 15\textsuperscript{th} version of the Enhanced Compression Model (ECM) software that explores…
Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency.…
Software bugs cost the global economy billions of dollars each year and take up ~50% of the development time. Once a bug is reported, the assigned developer attempts to identify and understand the source code responsible for the bug and…
Collective intelligence among gig workers yields considerable advantages, including improved information exchange, deeper social bonds, and stronger advocacy for better labor conditions. Especially as it enables workers to collaboratively…
Social coding platforms such as GitHub have become defacto environments for collaborative programming and open source. When these platforms do not support specific cognitive styles, they create barriers to programming for some populations.…
Formal mathematics has so far not taken full advantage of ideas from collaborative tools such as wikis and distributed version control systems (DVCS). We argue that the field could profit from such tools, serving both newcomers and experts…
Parallelism is a ubiquitous method for accelerating machine learning algorithms. However, theoretical analysis of parallel learning is usually done in an algorithm- and protocol-specific setting, giving little insight about how changes in…
Hybrid testing approaches that involve fuzz testing and symbolic execution have shown promising results in achieving high code coverage, uncovering subtle errors and vulnerabilities in a variety of software applications. In this paper we…
Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetuned models become publicly available, concerns about the…
Code translation aims to convert source code from one programming language (PL) to another. Given the promising abilities of large language models (LLMs) in code synthesis, researchers are exploring their potential to automate code…
Block-based programming environments such as Scratch are increasingly popular in programming education, in particular for young learners. While the use of blocks helps prevent syntax errors, semantic bugs remain common and difficult to…
The rapid advancement of artificial intelligence has elevated data to a cornerstone of modern software systems. As data projects become increasingly complex and dynamic, version control for data has become essential rather than merely…
Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe content, and a tendency…
Despite much recent interest in compiler randomized testing (fuzzing), the practical impact of fuzzer-found compiler bugs on real-world applications has barely been assessed. We present the first quantitative and qualitative study of the…
Fuzzing, a widely-used technique for bug detection, has seen advancements through Large Language Models (LLMs). Despite their potential, LLMs face specific challenges in fuzzing. In this paper, we identified five major challenges of…
Version control systems for source code, such as Git, are key tools in modern software development environments. Many developers use online services, such as GitHub or GitLab, for collaborative software development. While software projects…
The ability to cite software and give credit to its authors and contributors is increasingly important. While the number of online open-source software repositories has grown rapidly over the past few years, few are being properly cited…
As hardware components are becoming cheaper and powerful day by day, the expected services from modern software are increasing like any thing. Developing such software has become extremely challenging. Not only the complexity, but also the…