Related papers: LastMerge: A language-agnostic structured tool for…

Software vulnerabilities pose significant security challenges and potential risks to society, necessitating extensive efforts in automated vulnerability detection. There are two popular lines of work to address automated vulnerability…

In programming, better tools often yield better results. For that, modern programming environments offer mechanisms to allow for their extensibility. The closer those tools are to the code, the easier it is for programmers to map the…

We present a novel programming language design that attempts to combine the clarity and safety of high-level functional languages with the efficiency and parallelism of low-level numerical languages. We treat arrays as eagerly-memoized…

Background: Code summarization automatically generates the corresponding natural language descriptions according to the input code. Comprehensiveness of code representation is critical to code summarization task. However, most existing…

The development of large, software-intensive systems is a complex undertaking that we generally tackle by a divide and conquer strategy. Companies thereby face the challenge of coordinating individual aspects of software development, in…

Standard Byte-Pair Encoding (BPE) tokenization compresses text by pairing a learned token vocabulary with a detailed merge list. Recent work has shown that this merge list exposes a potential attack surface for extracting information about…

Context: The resolution of software merge conflicts is being reshaped by two competing paradigms: generative approaches based on Large Language Models (LLMs) and optimization approaches from Search-Based Software Engineering (SBSE). While…

We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to leverage their complementary strengths. One of the challenges of model fusion is high computational load, specifically in fine-tuning or aligning…

$k$-Nearest Neighbor search on dense vector embeddings ($k$-NN retrieval) from pre-trained embedding models is the predominant retrieval method for text and images, as well as Retrieval-Augmented Generation (RAG) pipelines. In practice,…

Loop transformations are semantics-preserving optimization techniques, widely used to maximize objectives such as parallelism. Despite decades of research, applying the optimal composition of loop transformations remains challenging due to…

The application of on-device language models (ODLMs) on resource-constrained edge devices is a multi-dimensional problem that strikes a fine balance between computational effectiveness, memory, power usage, and linguistic capacity across…

Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of…

Production assertions are statements embedded in the code to help developers validate their assumptions about the code. They assist developers in debugging, provide valuable documentation, and enhance code comprehension. Current research in…

Large Language Models (LLMs) have been increasingly used to optimize code efficiency. Evaluating their effectiveness and further suggesting optimization opportunities often rely on high-quality tests to demonstrate the performance…

Large language models (LLMs) show promise in code translation - the task of translating code written in one programming language to another language - due to their ability to write code in most programming languages. However, LLM's…

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples,…

Modern recommender systems trained on domain-specific data often struggle to generalize across multiple domains. Cross-domain sequential recommendation has emerged as a promising research direction to address this challenge; however,…

The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance. These methods typically include some way of selecting LoRAs from a…

In collaborative software development, multiple contributors frequently change the source code in parallel to implement new features, fix bugs, refactor existing code, and make other changes. These simultaneous changes need to be merged…