文档版式论文趋势 2023–2026
版式分析
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 28 篇被归入该主题的论文。
主要结论
- 文档版式论文从 2023 年的 6 篇增长到 2026 年的 8 篇，三年间扩大到约 1.3 倍。
- CVPR 是发文档版式论文最多的会议，2023–2026 年共 12 篇，占四个会议总量的 43%。
- 在「文档与版式」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的PDF 理解是 6.5 倍，文档版式是 1.3 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 1 | 1 | 1 | 3 | 6 |
| 2024 | 2 | 1 | 1 | 4 | 8 |
| 2025 | 1 | 2 | 1 | 2 | 6 |
| 2026 | 5 | 0 | 0 | 3 | 8 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- NeurIPS 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
- CVPR 2026DREAM Document Recognition with Explicit Adaptive Memory
- NeurIPS 2025Document Summarization with Conformal Importance Guarantees
- ICML 2025DeepLayout: Learning Neural Representations of Circuit Placement Layout
- ICLR 2025Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information
- CVPR 2025A Simple yet Effective Layout Token in Large Language Models for Document Understanding
- NeurIPS 2024Newswire: A Large-Scale Structured Database of a Century of Historical News
- ICML 2024Extracting Training Data From Document-Based VQA Models
- ICLR 2024LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
- CVPR 2024No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation
- NeurIPS 2023WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data
- ICML 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
- ICLR 2023StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
- CVPR 2023Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation With Cross-Scale Distortion Awareness
- NeurIPS 2026WordEval: Evaluating Word-Native Operation Fidelity in Document Editing
- CVPR 2026LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis
- ICLR 2025Graph-based Document Structure Analysis
- CVPR 2025Relation-Rich Visual Document Generator for Visual Information Extraction
- NeurIPS 2024VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
- CVPR 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
全部文档版式论文
共 28 篇，第 1 / 1 页
- CVPR 2026DREAM Document Recognition with Explicit Adaptive Memory
- CVPR 2026LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis
- CVPR 2026OmniDocLayout Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
- NeurIPS 2026From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning
- NeurIPS 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
- NeurIPS 2026The SEC Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
- NeurIPS 2026TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning
- NeurIPS 2026WordEval: Evaluating Word-Native Operation Fidelity in Document Editing
- CVPR 2025A Simple yet Effective Layout Token in Large Language Models for Document Understanding
- CVPR 2025Relation-Rich Visual Document Generator for Visual Information Extraction
- ICLR 2025Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information
- ICLR 2025Graph-based Document Structure Analysis
- ICML 2025DeepLayout: Learning Neural Representations of Circuit Placement Layout
- NeurIPS 2025Document Summarization with Conformal Importance Guarantees
- CVPR 2024DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks
- CVPR 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
- CVPR 2024No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation
- CVPR 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
- ICLR 2024LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
- ICML 2024Extracting Training Data From Document-Based VQA Models
- NeurIPS 2024Newswire: A Large-Scale Structured Database of a Century of Historical News
- NeurIPS 2024VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
- CVPR 2023Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation With Cross-Scale Distortion Awareness
- CVPR 2023M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
- CVPR 2023Unifying Vision, Text, and Layout for Universal Document Processing
- ICLR 2023StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
- ICML 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
- NeurIPS 2023WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查文档版式在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "document-layout"}
常见问题
- 2023–2026 年四大会议一共有多少篇文档版式论文？
- 共 28 篇，按年份分别是 2023 年 6 篇、2024 年 8 篇、2025 年 6 篇、2026 年 8 篇。
- NeurIPS 2026 有多少篇文档版式论文？
- NeurIPS 2026 有 5 篇文档版式论文，上一届是 1 篇。
- ICLR 2025 有多少篇文档版式论文？
- ICLR 2025 有 2 篇文档版式论文，上一届是 1 篇。
- ICML 2025 有多少篇文档版式论文？
- ICML 2025 有 1 篇文档版式论文，上一届是 1 篇。
- CVPR 2026 有多少篇文档版式论文？
- CVPR 2026 有 3 篇文档版式论文，上一届是 2 篇。
- 哪个会议的文档版式论文最多？
- CVPR，2023–2026 年共 12 篇。