相关论文: Katana: Dual Slicing-Based Context for Learning Bu…

Context of data points, which is usually defined as the other data points in a data set, has been found to play important roles in data representation and classification. In this paper, we study the problem of using context of a data point…

The predominant de facto paradigm of testing ML models relies on either using only held-out data to compute aggregate evaluation metrics or by assessing the performance on different subgroups. However, such data-only testing methods operate…

Context plays a crucial role in visual recognition as it provides complementary clues for different learning tasks including image classification and annotation. As the performances of these tasks are currently reaching a plateau, any extra…

Deep neural networks (DNNs) are becoming an integral part of most software systems. Previous work has shown that DNNs have bugs. Unfortunately, existing debugging techniques do not support localizing DNN bugs because of the lack of…

Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. We create and analyze a Journalist-provided Deepfake Dataset…

Surgical context inference has recently garnered significant attention in robot-assisted surgery as it can facilitate workflow analysis, skill assessment, and error detection. However, runtime context inference is challenging since it…

Test-based automated program repair has been a prolific field of research in software engineering in the last decade. Many approaches have indeed been proposed, which leverage test suites as a weak, but affordable, approximation to program…

The advance in machine learning (ML)-driven natural language process (NLP) points a promising direction for automatic bug fixing for software programs, as fixing a buggy program can be transformed to a translation task. While software…

This paper identifies the misinterpretation of the context can be a significant issue during the reasoning process of large language models, spanning from smaller models like Llama3.2-3B-Instruct to cutting-edge ones like DeepSeek-R1. For…

Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual…

Large language models (LLMs) have shown impressive effectiveness in various software engineering tasks, including automated program repair (APR). In this study, we take a deep dive into automated bug fixing utilizing LLMs. In contrast to…

In software development, fixing bugs is an important task that is time consuming and cost-sensitive. While many approaches have been proposed to automatically detect and patch software code, the strategies are limited to a set of identified…

Automatically locating buggy changesets associated with bug reports is crucial in the software development process. Deep Learning (DL)-based techniques show promising results by leveraging structural information from the code and learning…

Context parallelism has emerged as a key technique to support long-context training, a growing trend in generative AI for modern large models. However, existing context parallel methods rely on static parallelization configurations that…

Large language models (LLMs) with extended context windows enable tasks requiring extensive information integration but are limited by the scarcity of high-quality, diverse datasets for long-context instruction tuning. Existing data…

Vision models with high overall accuracy often exhibit systematic errors in specific scenarios, posing potential serious safety concerns. Diagnosing bugs of vision models is gaining increased attention, however traditional diagnostic…

In software development, encountering bugs is inevitable. However, opportunities to learn more about bug removal are limited. When students perform debugging tasks, they often use print statements because students do not know how to use a…

More and more languages have a need for constraint solving capabilities for features like error detection or automatic code generation. Imagine a dependently typed language that can immediately implement a program as soon as its type is…

Automatically fixing compilation errors can greatly raise the productivity of software development, by guiding the novice or AI programmers to write and debug code. Recently, learning-based program repair has gained extensive attention and…

We introduce a novel technique for finding real errors in programs. The technique is based on a synergy of three well-known methods: metacompilation, slicing, and symbolic execution. More precisely, we instrument a given program with a code…