Search Results

There has been a recent explosion of research on Large Language Models (LLMs) for software engineering tasks, in particular code generation. However, results from LLMs can be highly unstable; non-deterministically returning very different code for the ...

Automatic API recommendation can accelerate developers’ programming and has been studied for years. There are two orthogonal lines of approaches for this task, i.e., information retrieval-based (IR-based) approaches and sequence to sequence (seq2seq) ...

Composed image retrieval (CoIR) involves a multi-modal query of the reference image and modification text describing the desired changes, allowing users to express image retrieval intents flexibly and effectively. The key of CoIR lies in how to properly ...

The emergence of large language models is transforming various health-related domains, including approaches to obesity management. Obesity remains one of the world’s leading health issues, prompting the research community to develop various weight loss ...

This paper proposes LATTE, the first static binary taint analysis that is powered by a large language model (LLM). LATTE is superior to the state of the art (e.g., Emtaint, Arbiter, Karonte) in three aspects. First, LATTE is fully automated while prior ...

The shift to a service-oriented economy has driven traditional product-oriented manufacturing firms to integrate various services into their businesses. This study aims to provide empirical evidence on how manufacturers’ service offerings impact demand ...

Currently, large pre-trained language models are widely applied in neural code completion systems. Though large code models significantly outperform their smaller counterparts, around 70% of displayed code completions from Github Copilot are not accepted ...

Developers deal with code-change-related tasks daily, e.g., reviewing code. Pre-trained code and code-change-oriented models have been adapted to help developers with such tasks. Recently, large language models (LLMs) have shown their effectiveness in ...

Code reviews are central for software quality assurance. Ideally, reviewers should explain their feedback to enable authors of code changes to understand the feedback and act accordingly. Different developers might need different explanations in different ...

Synonym discovery is important in a wide variety of concept-related tasks, such as entity/concept mining and industrial knowledge graph (KG) construction. It intends to determine whether two terms refer to the same concept in semantics. Existing ...

Large language models (LLMs) have demonstrated strong performance across various natural language processing tasks and are increasingly integrated into daily life. Just as personality traits are crucial in human communication, they could also play a ...

Recent advancements in large language models (LLMs) integrated with external tools and APIs have successfully addressed complex tasks by using in-context learning or fine-tuning. Despite this progress, the vast scale of tool retrieval remains challenging ...

Recent advances in Large Language Models (LLMs) have significantly shaped the applications of AI in multiple fields, including the studies of legal intelligence. Trained on extensive legal texts, including statutes and legal documents, the legal LLMs can ...

Recent advancements in diffusion models have enabled a wide range of works exploiting their ability to generate high-volume, high-quality data for use in various downstream tasks. One subclass of such models, dubbed Layout-to-Image Synthesis (LIS),...

Artificial intelligence has emerged as a transformative force, driving productivity and shaping new forms of education. The future of education will be characterized by interactive learning, the blending of virtual and physical environments, and ...

Large Language Models (LLMs) have had considerable difficulty when prompted with mathematical and formal questions, especially those within theory of computing (ToC) courses. In this paper, we detail two experiments regarding our own ToC course and the ...

In programming language courses, many online platforms already feature extensive question banks. When teachers prepare course exercises, they need to select several programming problems of equivalent difficulty from the vast existing question bank so ...

Detecting human object interactions (HOI) involves localizing human-object pairs and recognizing the interaction between them. Recently, several HOI detection frameworks adopting Contrastive Language-Image Pre-training (CLIP) model have shown promising ...

Magic Data, in collaboration with M3Oriental, has jointly initiated the “Large-scale Multilingual Speech Recognition Challenge.” Centered on multilingualism, this challenge seeks to explore and develop advanced multilingual speech dialogue systems that ...

The integration of large language models (LLMs) in smart home systems holds significant promise for automating the generation of Trigger-Action Programming (TAP) rules, potentially streamlining smart home user experiences and enhancing convenience. ...