PDF Understanding papers, 2023–2026

Key findings

• PDF Understanding went from 6 papers in 2023 to 39 in 2026, roughly 6.5x in three years.
• CVPR publishes the most PDF Understanding work: 39 papers from 2023 to 2026, 38% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 1 in 2023 to 17 in 2026.
• Among the 5 topics under Document and Layout, it ranks #1 by 2026 paper count.

Representative papers

Spread across years and venues so every edition shows up

• 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

All PDF Understanding papers

35 papers, page 1 of 1

1. CVPR 2025A Simple yet Effective Layout Token in Large Language Models for Document Understanding
2. CVPR 2025AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
3. CVPR 2025Adaptive Keyframe Sampling for Long Video Understanding
4. CVPR 2025Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding
5. CVPR 2025BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
6. CVPR 2025DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
7. CVPR 2025Docopilot: Improving Multimodal Models for Document-Level Understanding
8. CVPR 2025DrVideo: Document Retrieval Based Long Video Understanding
9. CVPR 2025DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding
10. CVPR 2025Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images
11. CVPR 2025Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
12. CVPR 2025Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
13. CVPR 2025OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
14. CVPR 2025Re-thinking Temporal Search for Long-Form Video Understanding
15. CVPR 2025ReWind: Understanding Long Videos with Instructed Learnable Memory
16. CVPR 2025SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding
17. CVPR 2025Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
18. CVPR 2025VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
19. ICLR 2025Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
20. ICLR 2025Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information
21. ICLR 2025LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
22. ICLR 2025mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
23. ICLR 2025Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
24. ICLR 2025SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
25. ICLR 2025SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
26. ICLR 2025TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
27. ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
28. ICML 2025Position: Deep Learning is Not So Mysterious or Different
29. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
30. NeurIPS 2025FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
31. NeurIPS 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
32. NeurIPS 2025PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding
33. NeurIPS 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
34. NeurIPS 2025Unleashing Hour-Scale Video Training for Long Video-Language Understanding
35. NeurIPS 2025VideoLucy: Deep Memory Backtracking for Long Video Understanding

FAQ

How many PDF Understanding papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

102 in total: 6 in 2023, 22 in 2024, 35 in 2025, 39 in 2026.

How many PDF Understanding papers are at NeurIPS 2026?

NeurIPS 2026 has 21 PDF Understanding papers, versus 6 the year before.

How many PDF Understanding papers are at ICLR 2026?

ICLR 2026 has 6 PDF Understanding papers, versus 8 the year before.

How many PDF Understanding papers are at ICML 2026?

ICML 2026 has 2 PDF Understanding papers, versus 3 the year before.

How many PDF Understanding papers are at CVPR 2026?

CVPR 2026 has 10 PDF Understanding papers, versus 18 the year before.

Which conference publishes the most PDF Understanding papers?

CVPR, with 39 papers from 2023 to 2026.