Related papers: Multi-Stage JavaScript
Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full…
Multi-modal Retrieval-Augmented Generation (MMRAG) enables highly credible generation by integrating external multi-modal knowledge, thus demonstrating impressive performance in complex multi-modal scenarios. However, existing MMRAG methods…
The code generation capabilities of Large Language Models (LLMs) have advanced applications like tool invocation and problem-solving. However, improving performance in code-related tasks remains challenging due to limited training data that…
Logging is indispensable for maintaining the reliability and diagnosability of modern software, yet developers still struggle to decide where and how to log effectively. Existing automated logging techniques focus on isolated sub-tasks -…
As large language models become increasingly capable of generating code, evaluating their performance remains a complex and evolving challenge. Existing benchmarks primarily focus on functional correctness, overlooking the diversity of…
When programming network functions, changes within a packet tend to have consequences---side effects which must be accounted for by network programmers or administrators via arbitrary logic and an innate understanding of dependencies.…
Reranking, as the final stage of multi-stage recommender systems, refines the initial lists to maximize the total utility. With the development of multimedia and user interface design, the recommendation page has evolved to a multi-list…
Refactoring is the art of improving the design of a system without altering its external behavior. Refactoring has become a well established and disciplined software engineering practice that has attracted a significant amount of research…
Machine Learning software documentation is different from most of the documentations that were studied in software engineering research. Often, the users of these documentations are not software experts. The increasing interest in using…
Multimodal LLMs (MLLMs) have emerged as an extension of Large Language Models (LLMs), enabling the integration of various modalities. However, Any-to-Any MLLMs are limited to generating pairwise modalities 'Text + X' within a single…
The JavaScript programming language, which began as a simple scripting language for the Web, has become ubiquitous, spanning desktop, mobile, and server applications. This increase in usage has made JavaScript an attractive target for…
Large Language Models (LLMs) have achieved strong performance across a wide range of natural language processing tasks in recent years, including machine translation, text generation, and question answering. As their applications extend to…
Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce results and build upon prior work. In the meantime, recent…
This paper describes how to adapt a static code analyzer to help novice programmers. Current analyzers have been built to give feedback to experienced programmers who build new applications or systems. The type of feedback and the type of…
We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare…
Existing knowledge-grounded dialogue systems typically use finetuned versions of a pretrained language model (LM) and large-scale knowledge bases. These models typically fail to generalize on topics outside of the knowledge base, and…
Data engineers increasingly use domain-specific languages (DSLs) to generate the code for data pipelines. Such DSLs are often embedded in Python. Unfortunately, there are challenges in debugging the generation of data pipelines: an error in…
The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast amounts of labor to keep them tested, maintained, and up to date. As the…
Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting…
Code editing constitutes a fundamental practice in software development, wherein developers modify existing codebases according to natural language requirements. Accurate code editing necessitates a comprehensive understanding of both the…