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

102 papers, page 2 of 3

51. CVPR 2025Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
52. CVPR 2025OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
53. CVPR 2025Re-thinking Temporal Search for Long-Form Video Understanding
54. CVPR 2025ReWind: Understanding Long Videos with Instructed Learnable Memory
55. CVPR 2025SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding
56. CVPR 2025Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
57. CVPR 2025VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
58. ICLR 2025Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
59. ICLR 2025Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information
60. ICLR 2025LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
61. ICLR 2025mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
62. ICLR 2025Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
63. ICLR 2025SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
64. ICLR 2025SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
65. ICLR 2025TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
66. ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
67. ICML 2025Position: Deep Learning is Not So Mysterious or Different
68. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
69. NeurIPS 2025FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
70. NeurIPS 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
71. NeurIPS 2025PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding
72. NeurIPS 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
73. NeurIPS 2025Unleashing Hour-Scale Video Training for Long Video-Language Understanding
74. NeurIPS 2025VideoLucy: Deep Memory Backtracking for Long Video Understanding
75. CVPR 2024Action Scene Graphs for Long-Form Understanding of Egocentric Videos
76. CVPR 2024Compositional Video Understanding with Spatiotemporal Structure-based Transformers
77. CVPR 2024Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
78. CVPR 2024Grounded Question-Answering in Long Egocentric Videos
79. CVPR 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
80. CVPR 2024MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
81. CVPR 2024TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
82. ICLR 2024ADOPD: A Large-Scale Document Page Decomposition Dataset
83. ICLR 2024Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
84. ICLR 2024Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
85. ICLR 2024Nougat: Neural Optical Understanding for Academic Documents
86. ICML 2024Extracting Training Data From Document-Based VQA Models
87. ICML 2024Memory Consolidation Enables Long-Context Video Understanding
88. ICML 2024Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
89. ICML 2024Understanding Unimodal Bias in Multimodal Deep Linear Networks
90. NeurIPS 2024Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
91. NeurIPS 2024HourVideo: 1-Hour Video-Language Understanding
92. NeurIPS 2024LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
93. NeurIPS 2024MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
94. NeurIPS 2024MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
95. NeurIPS 2024Newswire: A Large-Scale Structured Database of a Century of Historical News
96. NeurIPS 2024SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
97. CVPR 2023Long Range Pooling for 3D Large-Scale Scene Understanding
98. CVPR 2023Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding
99. CVPR 2023Selective Structured State-Spaces for Long-Form Video Understanding
100. CVPR 2023Self-Positioning Point-Based Transformer for Point Cloud 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.