arXiv:2606. 16494v1 Announce Type: cross Abstract: Knowledge-based visual question answering (KB-VQA) lets vision-language systems answer questions that exceed their parametric knowledge by conditioning a reader on passages retrieved from a Wikipedia-scale knowledge base.
arXiv:2607. 05438v1 Announce Type: cross Abstract: Multimodal retrieval-augmented generation (RAG) grounds a generator in evidence drawn from heterogeneous modalities -- text, tables, and images.
Multimodal LLMs can see a document, but they often can't read it reliably. Small text, tables, visual cues, and topological elements still trip them up under direct visual inference, even when the pag...
arXiv:2605.27243v3 Announce Type: replace Abstract: Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent traject...
arXiv:2607. 25422v1 Announce Type: new Abstract: Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense retrieval over large external corpora, and full cross-modal fusion.
arXiv:2604.27724v2 Announce Type: replace Abstract: Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich vis...
arXiv:2608. 19739v1 Announce Type: cross Abstract: Multimodal LLMs can see a document, but they often can't read it reliably.
arXiv:2411. 15041v2 Announce Type: replace Abstract: Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based Visual Question Answering (VQA) tasks, such as INFOSEEK and Encyclopedic-VQA, due to their limited and frozen knowledge scope, often leading to ambiguous and inaccurate responses.
arXiv:2602. 00344v2 Announce Type: replace-cross Abstract: While Retrieval-Augmented Generation (RAG) is one of the dominant paradigms for enhancing Large Vision-Language Models (LVLMs) on knowledge-based VQA tasks, recent work attributes RAG failures to insufficient attention towards the retrieved context, proposing to reduce the attention allocated to image tokens.
arXiv:2607. 14682v1 Announce Type: new Abstract: Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge.
arXiv:2607. 15565v1 Announce Type: cross Abstract: Where should the question go in a vision-language model (VLM) prompt: before the image or after it?
arXiv:2606. 04240v1 Announce Type: cross Abstract: Retrieval over visually-rich documents, pages that interleave text with figures, tables, and charts, is essential for multimodal retrieval-augmented generation, yet most retrievers still discard the visual channel.
MIDR (Multimodal Indexing for Document Retrieval) is a training‑free framework that enriches document indexes by converting rendered pages into verified textual fields with a multimodal LLM, then indexing those fields with BM25F and optionally fusing with dense retrieval. By shifting multimodal reasoning to index time, MIDR enables text‑centric serving while retaining multimodal evidence, achieving a 23.0% relative gain over BM25 on ViDoRe V3 and outperforming ColQwen2.5 on several domains with significantly smaller index memory and lower query latency.