Harnessing Webpage UIs for Text-Rich Visual Understanding
원문 초록
Text-rich visual understanding-the ability to process environments where dense textual content is integrated with visuals-is crucial for multimodal large language models (MLLMs) to interact effectively with structured environments. To enhance this capability, we propose synthesizing general multimodal instructions from webpage UIs using text-based large language models (LLMs). Despite lacking direct visual input, text-based LLMs are able to process structured text representations from webpage accessibility trees. These instructions are then paired with UI screenshots to train multimodal models. We introduce MultiUI, a dataset containing 7.3 million samples from 1 million websites, covering diverse multimodal tasks and UI layouts. Models trained on MultiUI not only excel in web UI tasks-achieving up to a 48% improvement on VisualWebBench and a 19.1% boost in element accuracy on a web agent dataset Mind2Web-but also generalize surprisingly well to non-web UI tasks and even to non-UI domains, such as document understanding, OCR, and chart interpretation. These results highlight the broad applicability of web UI data for advancing text-rich visual understanding across various scenarios.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PaddleOCR 3.0 Technical Report
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark
Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language Models
Relation-Rich Visual Document Generator for Visual Information Extraction
BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.