DocSynthv2: A Practical Autoregressive Modeling for Document Generation
This addresses the complex challenge of comprehensive document generation for automated design, though it appears incremental as it builds on layout-generation approaches.
The paper tackled the problem of generating documents with both layout and content, proposing DocSynthv2, an autoregressive model that integrates layout and textual cues to produce cohesive documents without visual components, demonstrating enhanced generation quality and relevance on a curated benchmark.
While the generation of document layouts has been extensively explored, comprehensive document generation encompassing both layout and content presents a more complex challenge. This paper delves into this advanced domain, proposing a novel approach called DocSynthv2 through the development of a simple yet effective autoregressive structured model. Our model, distinct in its integration of both layout and textual cues, marks a step beyond existing layout-generation approaches. By focusing on the relationship between the structural elements and the textual content within documents, we aim to generate cohesive and contextually relevant documents without any reliance on visual components. Through experimental studies on our curated benchmark for the new task, we demonstrate the ability of our model combining layout and textual information in enhancing the generation quality and relevance of documents, opening new pathways for research in document creation and automated design. Our findings emphasize the effectiveness of autoregressive models in handling complex document generation tasks.