PDF 理解论文趋势 2023–2026

主要结论

• PDF 理解论文从 2023 年的 6 篇增长到 2026 年的 39 篇，三年间扩大到约 6.5 倍。
• CVPR 是发PDF 理解论文最多的会议，2023–2026 年共 39 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 17 篇。
• 在「文档与版式」的 5 个主题里，它的 2026 年论文数排第 1。

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 2026DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding
• ICML 2026Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
• ICLR 2026Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Understanding
• CVPR 2026MS-Temba Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos
• NeurIPS 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
• ICML 2025Position: Deep Learning is Not So Mysterious or Different
• ICLR 2025Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
• CVPR 2025Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images
• NeurIPS 2024SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
• ICML 2024Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
• ICLR 2024Nougat: Neural Optical Understanding for Academic Documents
• CVPR 2024Action Scene Graphs for Long-Form Understanding of Egocentric Videos
• NeurIPS 2023Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective
• ICLR 2023Understanding Edge-of-Stability Training Dynamics with a Minimalist Example
• CVPR 2023Long Range Pooling for 3D Large-Scale Scene Understanding
• NeurIPS 2026Towards Understanding Momentum Acceleration in River-Valley Loss Landscape
• ICML 2026SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
• ICLR 2026Understanding the Learning Phases in Self-Supervised Learning via Critical Periods
• CVPR 2026Understanding Accelerating and Improving MeanFlow Training
• NeurIPS 2025PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding

全部PDF 理解论文

共 39 篇，第 1 / 1 页

1. CVPR 2026AdaSpark Adaptive Sparsity for Efficient Long-Video Understanding
2. CVPR 2026Efficient Frame Selection for Long Video Understanding via Reinforcement Learning
3. CVPR 2026META Meta Evolution of Tool Trajectory Adaptation for Long-Video Understanding
4. CVPR 2026MS-Temba Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos
5. CVPR 2026Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding
6. CVPR 2026Scaling the Long Video Understanding of Multimodal Large Language Models
7. CVPR 2026Understanding Accelerating and Improving MeanFlow Training
8. CVPR 2026Video Panels for Long Video Understanding
9. CVPR 2026VideoARM Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
10. CVPR 2026VirtueBench Evaluating Trustworthiness under Uncertainty in Long Video Understanding
11. CVPR 2025A Simple yet Effective Layout Token in Large Language Models for Document Understanding
12. CVPR 2025AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
13. CVPR 2025Adaptive Keyframe Sampling for Long Video Understanding
14. CVPR 2025Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding
15. CVPR 2025BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
16. CVPR 2025DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
17. CVPR 2025Docopilot: Improving Multimodal Models for Document-Level Understanding
18. CVPR 2025DrVideo: Document Retrieval Based Long Video Understanding
19. CVPR 2025DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding
20. CVPR 2025Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images
21. CVPR 2025Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
22. CVPR 2025Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
23. CVPR 2025OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
24. CVPR 2025Re-thinking Temporal Search for Long-Form Video Understanding
25. CVPR 2025ReWind: Understanding Long Videos with Instructed Learnable Memory
26. CVPR 2025SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding
27. CVPR 2025Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
28. CVPR 2025VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
29. CVPR 2024Action Scene Graphs for Long-Form Understanding of Egocentric Videos
30. CVPR 2024Compositional Video Understanding with Spatiotemporal Structure-based Transformers
31. CVPR 2024Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
32. CVPR 2024Grounded Question-Answering in Long Egocentric Videos
33. CVPR 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
34. CVPR 2024MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
35. CVPR 2024TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
36. CVPR 2023Long Range Pooling for 3D Large-Scale Scene Understanding
37. CVPR 2023Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding
38. CVPR 2023Selective Structured State-Spaces for Long-Form Video Understanding
39. CVPR 2023Self-Positioning Point-Based Transformer for Point Cloud Understanding

常见问题

2023–2026 年四大会议一共有多少篇PDF 理解论文？

共 102 篇，按年份分别是 2023 年 6 篇、2024 年 22 篇、2025 年 35 篇、2026 年 39 篇。

NeurIPS 2026 有多少篇PDF 理解论文？

NeurIPS 2026 有 21 篇PDF 理解论文，上一届是 6 篇。

ICLR 2026 有多少篇PDF 理解论文？

ICLR 2026 有 6 篇PDF 理解论文，上一届是 8 篇。

ICML 2026 有多少篇PDF 理解论文？

ICML 2026 有 2 篇PDF 理解论文，上一届是 3 篇。

CVPR 2026 有多少篇PDF 理解论文？

CVPR 2026 有 10 篇PDF 理解论文，上一届是 18 篇。

哪个会议的PDF 理解论文最多？

CVPR，2023–2026 年共 39 篇。