Related papers: Targeted Test Selection Approach in Continuous Int…

We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we…

We introduce an adaptive scheduling for adaptive sampling as a novel way of machine learning in the construction of part-of-speech taggers. The goal is to speed up the training on large data sets, without significant loss of performance…

We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical…

Technology Assisted Review (TAR), which aims to reduce the effort required to screen collections of documents for relevance, is used to develop systematic reviews of medical evidence and identify documents that must be disclosed in response…

Large language models (LLMs) have recently achieved significant success across various application domains, garnering substantial attention from different communities. Unfortunately, even for the best LLM, many \textit{faults} still exist…

In the last decade, an impressive increase in software adaptions has led to a surge in log data production, making manual log analysis impractical and establishing the necessity for automated methods. Conversely, most automated analysis…

Abstract End-to-end text-to-speech (TTS) systems has proved its great success in the presence of a large amount of high-quality training data recorded in anechoic room with high-quality microphone. Another approach is to use available…

Selecting high-quality training data from a larger pool is a crucial step when instruction-tuning language models, as carefully curated datasets often produce models that outperform those trained on much larger, noisier datasets. Automated…

Much work has been done on feature selection. Existing methods are based on document frequency, such as Chi-Square Statistic, Information Gain etc. However, these methods have two shortcomings: one is that they are not reliable for…

In dynamic selection (DS) techniques, only the most competent classifiers, for the classification of a specific test sample are selected to predict the sample's class labels. The more important step in DES techniques is estimating the…

Software faults are commonly occurred due to interactions between one or more input parameters in complex software systems. Software test design techniques can be implemented to ensure the quality of the developed software. Exhaustive…

Test suite reduction (TSR) aims at removing redundant test cases from regression test suites. A typical TSR approach ensures that structural profile elements covered by the original test suite are also covered by the reduced test suite. It…

Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the…

Large language models (LLMs) have demonstrated significant potential in code generation tasks. However, there remains a performance gap between open-source and closed-source models. To address this gap, existing approaches typically…

Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of language model-based TTS models. Current approaches primarily require…

To maintain the accuracy of supervised learning models in the presence of evolving data streams, we provide temporally-biased sampling schemes that weight recent data most heavily, with inclusion probabilities for a given data item decaying…

Inspections and testing are two of the most commonly performed software quality assurance processes today. Typically, these processes are applied in isolation, which, however, fails to exploit the benefits of systematically combining and…

Testing of software or software-based systems and services is considered as one of the most effort-consuming activities in the lifecycle. This applies especially to those domains where highly iterative development and continuous integration…

Background. Software Engineering (SE) researchers extensively perform experiments with human subjects. Well-defined samples are required to ensure external validity. Samples are selected \textit{purposely} or by \textit{convenience},…

Recent work shows that post-training datasets for LLMs can be substantially downsampled without noticeably deteriorating performance. However, data selection often incurs high computational costs or is limited to narrow domains. In this…