Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing

arXiv:2609.23592 · cs.CV, cs.CL · Submitted 2026-09-20 · Read on arXiv

cs.CV, cs.CL

Submitted: 2026-09-20

Updated: 2026-09-20

Comments: 5 pages, 3 figures, 2 tables. Submitted to ICASSP 2027

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 7× in this paper · explained in 2 episodes
• Trace — 5× in this paper · explained in 2 episodes
• AUROC — 4× in this paper · explained in 2 episodes
• Vision-language models — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 2× in this paper
• Meeting of the Association for Computational Linguistics — 2× in this paper
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Qianfan-OCR: A Unified End-to-End Model for Document Intelligence
• PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
• Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning
• Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
• Pre-Inference Routing for Cost-Efficient Document Field Extraction
• Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
• DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM
• LayoutLite: Token-Level Implicit Layout Analysis for Efficient Document OCR
• How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings
• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
• GLM-OCR Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models