Related papers: Auto-Icon+: An Automated End-to-End Code Generatio…

State-of-the-art computer vision approaches rely on huge amounts of annotated data. The collection of such data is a time consuming process since it is mainly performed by humans. The literature shows that semi-automatic annotation…

Highly customized graphical user interfaces play a major role in today's software applications. There exist many technologies that support developing them. But these technologies demand writing a significant amount of unintuitive code to…

Automated understanding of user interfaces (UIs) from their pixels can improve accessibility, enable task automation, and facilitate interface design without relying on developers to comprehensively provide metadata. A first step is to…

Design inspiration is crucial for establishing the direction of a design as well as evoking feelings and conveying meanings during the conceptual design process. Many practice designers use text-based searches on platforms like Pinterest to…

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this…

Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we present CodeCompose, an AI-assisted code authoring tool…

We address the problem of computing the distribution of induced connected subgraphs, aka \emph{graphlets} or \emph{motifs}, in large graphs. The current state-of-the-art algorithms estimate the motif counts via uniform sampling, by…

Customization of text-to-image models enables users to insert new concepts or objects and generate them in unseen settings. Existing methods either rely on comparatively expensive test-time optimization or train encoders on single-image…

Text-to-image diffusion models have significantly improved the seamless integration of visual text into diverse image contexts. Recent approaches further improve control over font styles through fine-tuning with predefined font…

We propose AutoLegend to generate interactive visualization legends using online learning with user feedback. AutoLegend accurately extracts symbols and channels from visualizations and then generates quality legends. AutoLegend enables a…

Developing models that can automatically generate detailed code explanation can greatly benefit software maintenance and programming education. However, existing code-to-text generation models often produce only high-level summaries of code…

Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or…

Software design techniques are undoubtedly crucial in the process of designing good software. Over the years, a large number of design techniques have been proposed by both researchers and practitioners. Unfortunately, despite their…

Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent. However, given NL is informal, it does not lend easily to checking…

Many applications require categorization of text documents using predefined categories. The main approach to performing text categorization is learning from labeled examples. For many tasks, it may be difficult to find examples in one…

Code completion plays a prominent role in modern integrated development environments (IDEs). Machine learning has become ubiquitous in analogous natural language writing and search software, surfacing more relevant autocompletions and…

Autonomous GUI agents interact with environments by perceiving interfaces and executing actions. As a virtual sandbox, the GUI World model empowers agents with human-like foresight by enabling action-conditioned prediction. However,…

Low-code programming allows citizen developers to create programs with minimal coding effort, typically via visual (e.g. drag-and-drop) interfaces. In parallel, recent AI-powered tools such as Copilot and ChatGPT generate programs from…

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…

Programmers often reuse code from source code repositories to reduce the development effort. Code clones are candidates for reuse in exploratory or rapid development, as they represent often repeated functionality in software systems. To…