相关论文: HTMLCure: Turning Browser Experience into State Gu…

Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extracting structured information from them remains challenging.…

Multimodal large language models (MLLMs) are increasingly deployed as the core reasoning engine for web-facing systems, powering GUI agents and front-end automation that must interpret page structure, select actionable widgets, and execute…

Large language models (LLMs) are increasingly used for automated code refactoring tasks. Although these models can quickly refactor code, the quality may exhibit inconsistencies and unpredictable behavior. In this article, we systematically…

The integration of Large Language Models (LLMs) into browser extensions has revolutionized web browsing, enabling sophisticated functionalities like content summarization, intelligent translation, and context-aware writing assistance.…

Using vision-language models (VLMs) in web development presents a promising strategy to increase efficiency and unblock no-code solutions: by providing a screenshot or a sketch of a UI, a VLM could generate the code to reproduce it, for…

We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardized corpus of 240T tokens extracted from Common Crawl,…

We conduct a large-scale empirical user study in a live setup to evaluate the acceptance of LLM-generated comments and their impact on the review process. This user study was performed in two organizations, Mozilla (which has its codebase…

Evaluating machine-generated text remains a significant challenge in NLP, especially for non-English languages. Current methodologies, including automated metrics, human assessments, and LLM-based evaluations, predominantly focus on…

Evaluating language models in streaming environments is critical, yet underexplored. Existing benchmarks either focus on single complex events or provide curated inputs for each query, and do not evaluate models under the conflicts that…

Sketches are a natural and accessible medium for UI designers to conceptualize early-stage ideas. However, existing research on UI/UX automation often requires high-fidelity inputs like Figma designs or detailed screenshots, limiting…

Large Language Models (LLMs) have demonstrated significant potential in various engineering tasks, including software development, digital logic generation, and companion document maintenance. However, their ability to perform board-level…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

Real-world information, often multimodal, can be misinformed or potentially misleading due to factual errors, outdated claims, missing context, misinterpretation, and more. Such "misinformation" is understudied, challenging to address, and…

Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with…

With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for…

Web navigation is a unique domain that can automate many repetitive real-life tasks and is challenging as it requires long-horizon sequential decision making beyond typical multimodal large language model (MLLM) tasks. Yet, specialized…

Large Language Models (LLMs) are increasingly used to refactor unit tests, improving readability and structure while preserving behavior. Evaluating such refactorings, however, remains difficult: metrics like CodeBLEU penalize beneficial…

Multimodal Large Language Models (MLLMs) are evaluated on various benchmarks, such as image captioning, visual question answering, and reasoning. However, many of these benchmarks include overly simple or uninformative samples, complicating…

Modern web scraping struggles with dynamic, interactive websites that require more than static HTML parsing. Current methods are often brittle and require manual customization for each site. To address this, we introduce Webscraper, a…

Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluations offer limited coverage, imprecise target-state definitions, and an overreliance on…