arXiv AI September 23, 2026 By Nikhil Reddy Pottanigari, Sepideh Kharaghani, Saverio Vadacchino, Alejandro Posada, Ying Zhang

Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document QA

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

multimodal

Hugging Face Trending Papers

Aug 20

Question-Guided Evidence Acquisition for Multimodal Visual Question Answering

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...

llms agents nlp multimodal

arXiv AI

Aug 21

Question-Guided Evidence Acquisition for Multimodal Visual Question Answering

arXiv:2608. 19739v1 Announce Type: cross Abstract: Multimodal LLMs can see a document, but they often can't read it reliably.

By Alin-Ionut Popa

llms agents nlp multimodal

arXiv AI

Aug 25

Query-Driven Multimodal Information Extraction from Long Documents

arXiv:2608.22214v1 Announce Type: new Abstract: In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. Howev...

By Yikai Gao, Ding Xia, Xi Yang

llms agents multimodal benchmarks

arXiv Computer Vision

Sep 1

Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models

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...

By Aaron Branson Cigres Li, Zhaowei Wang, Yu Zhao, Yiming Du, Haobo Li, Xiyu Ren, Ginny Wong, Simon See, Lishu Luo, Haodong Duan, Pasquale Minervini, Yangqiu Song

llms agents multimodal

arXiv AI

Jun 30

PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation

arXiv:2606. 28344v1 Announce Type: cross Abstract: Augmenting large language models (LLMs) with retrieved web text has become a dominant paradigm, yet the web is not natively textual: existing systems depend on complex parsing pipelines that linearize HTML and discard layout, visual structure, and formatting.

By Yichuan Wang, Zhifei Li, Zirui Wang, Paul Teiletche, Lesheng Jin, Matei Zaharia, Joseph E. Gonzalez, Sewon Min

llms rag agents multimodal benchmarks

arXiv AI

Sep 15

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering

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...

By Xupeng Chen, Binbin Shi, Chenqian Le, Jiaqi Zhang, Kewen Wang, Ran Gong, Jinhan Zhang, Chihang Wang

llms rag computer-vision nlp multimodal benchmarks

One email a morning, machine-written

Related stories

Question-Guided Evidence Acquisition for Multimodal Visual Question Answering

Question-Guided Evidence Acquisition for Multimodal Visual Question Answering

Query-Driven Multimodal Information Extraction from Long Documents

Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models

PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering