Browsing: Document

arXiv:2603.12249v1 Announce Type: cross Abstract: Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among…

arXiv:2602.12278v1 Announce Type: cross Abstract: Retrieval augmented generation (RAG) has been widely adopted to help Large Language Models (LLMs) to…

Running a business involves a lot of important documents: contracts, employee onboarding information, financial and tax records, meeting minutes, process…

[Submitted on 22 Nov 2025 (v1), last revised 28 Nov 2025 (this version, v2)] View a PDF of the paper…