arXiv Computation and Language September 23, 2026 By Luca Foppiano, Sana Khamassi, Vipul Gupta

Layout-Guided Masking for GROBID: Lightweight Structural Gains in Large-Scale Scientific PDF Ingestion

Read the original on arXiv Computation and Language →

The paper introduces a lightweight CPU-based extension to GROBID that uses layout-guided masking to identify figure, table, and paratext regions in scientific PDFs. By routing tokens to specialized GROBID models or discarding them, the method improves structural accuracy on PMC corpora and enhances figure caption recovery. It also achieves competitive table detection and body‑text precision compared to vision‑based GPU parsers while operating entirely on CPU and costing significantly less.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Computer Vision

Sep 22

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

arXiv:2609.24220v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presen...

By Uday Allu (AI Research Team Yellow.ai), Abhivanth Sivaprakash (AI Research Team Yellow.ai), Pratik Singh (AI Research Team Yellow.ai), Aman Manocha (AI Research Team Yellow.ai)

llms rag agents computer-vision multimodal benchmarks safety

arXiv Computer Vision

1d ago

Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models

arXiv:2610.02880v1 Announce Type: new Abstract: Retrieval-augmented document question answering assumes that once the right page is found, a vision-language model (VLM) can read it. We show that this...

By Qingtao Xia, Siyao Cheng, Jiahua Bao, Jiaxing Du, Jie Liu

llms rag computer-vision nlp multimodal benchmarks

arXiv AI

Aug 18

LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents

arXiv:2608. 15064v1 Announce Type: new Abstract: Parsing visual documents into machine-readable representations is fundamental to document intelligence.

By Yuefeng Zou, Yichen Lu, Jingxiao Yang, Bingtao Fu, Gaoyang Zhang, Xiongfei Bai, Tian Chen, Xiang Qi

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

arXiv AI

Aug 3

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

arXiv:2607. 29677v1 Announce Type: new Abstract: Enterprise workflows increasingly rely on agents for \emph{schema-guided extraction}: given a document and a user-defined schema, the agent faithfully follows the schema to produce the correct output with source evidence as grounding metadata.

By Boyang Zhang, Adrian Lyjak, Eli Stewart, Zhaoqi Li, Simon Suo

llms agents benchmarks

arXiv Computation and Language

Sep 4

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

Jina-OCR-v1 is an end‑to‑end document parsing model designed for low‑budget GPUs, combining a compressed‑vision encoder with a 3B mixture‑of‑experts decoder that activates about 570 M parameters per token. It uses a FastMTP speculative decoding head that shares a single draft block across three prediction steps, with greedy verification ensuring lossless decoding. Post‑training includes instruction alignment, robustness fine‑tuning on difficult documents, and GRPO with dense verifiable rewards, achieving 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR‑Bench while delivering the highest page throughput at 2.57 pages per second on an NVIDIA L4 GPU.

By Alejandro Bar\'on Garc\'ia, Feng Wang, Emilia Garcia Casademont, Han Xiao

computer-vision fine-tuning efficiency safety

One email a morning, machine-written

Related stories

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models

LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards