·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
An AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response5m◆Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training5m◆Large language model and reinforcement learning based autonomous construction and progress updates5m◆Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models5m◆MedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring5m◆DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution5m◆Industrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing5m◆Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 45m◆MAMath-Bench: Process-Aware and Robust Evaluation of Multimodal Multi-Agent Mathematical Reasoning5m◆LightCRS: Lightweight Multi-Domain Conversational Recommendation System5m◆When Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic Interpretability5m◆SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents5m◆Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?5m◆Teaching AI Agent to Play Poker Strategically Through Preference Optimization5m◆M-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement5m◆Physical AI: Concepts, Techniques, and Challenges5m◆ReuF2F: Benchmarking Coding Agents on Formalized Undergraduate Research Problems5m◆A general-purpose System One decision model for clinical records5m◆Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs5m◆PROVISO: Provenance-Informed Action Selection for Secure LLM Agents5m◆An AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response5m◆Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training5m◆Large language model and reinforcement learning based autonomous construction and progress updates5m◆Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models5m◆MedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring5m◆DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution5m◆Industrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing5m◆Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 45m◆MAMath-Bench: Process-Aware and Robust Evaluation of Multimodal Multi-Agent Mathematical Reasoning5m◆LightCRS: Lightweight Multi-Domain Conversational Recommendation System5m◆When Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic Interpretability5m◆SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents5m◆Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?5m◆Teaching AI Agent to Play Poker Strategically Through Preference Optimization5m◆M-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement5m◆Physical AI: Concepts, Techniques, and Challenges5m◆ReuF2F: Benchmarking Coding Agents on Formalized Undergraduate Research Problems5m◆A general-purpose System One decision model for clinical records5m◆Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs5m◆PROVISO: Provenance-Informed Action Selection for Secure LLM Agents5m◆
News/MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
arxiv
PublishedMay 29, 2026 at 4:00 AM
—neutral

MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.22100v2 Announce Type: replace Abstract: Document parsing converts visually rich documents into machine-readable structured representations, forming a crucial foundation for information systems. Although many benchmarks have been proposed for document parsing, they remain inadequate for r

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#document-parsing#benchmark#information-systems#multi-page

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#document-parsing#benchmark#information-systems#multi-page
The Bubble Brief
MON · WED · FRI

Read document-parsing insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews