信息抽取论文趋势 2023–2026

主要结论

• 信息抽取论文从 2023 年的 143 篇增长到 2026 年的 266 篇，三年间扩大到约 1.9 倍。
• NeurIPS 是发信息抽取论文最多的会议，2023–2026 年共 287 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 28 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的检索增强生成是 5.4 倍，信息抽取是 1.9 倍。

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 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
• ICLR 2026An Information-Theoretic Parameter-Free Bayesian Framework for Probing Labeled Dependency Trees from Attention Score
• CVPR 2026ActiveGrasp Information-Guided Active Grasping with Calibrated Energy-based Model
• NeurIPS 2025A Pre-training Framework for Relational Data with Information-theoretic Principles
• ICML 2025A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method
• ICLR 2025ADAM: An Embodied Causal Agent in Open-World Environments
• CVPR 2025A Focused Human Body Model for Accurate Anthropometric Measurements Extraction
• NeurIPS 2024TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
• ICML 2024An Information-Theoretic Analysis of In-Context Learning
• ICLR 2024Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
• CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
• NeurIPS 2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective
• ICML 2023Abstracting Imperfect Information Away from Two-Player Zero-Sum Games
• ICLR 2023A VAE for Transformers with Nonparametric Variational Information Bottleneck
• CVPR 2023"Seeing" Electric Network Frequency From Events
• NeurIPS 2026An Information-theoretic Framework for Auditing Unfairness in Training Data
• ICML 2026GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation
• ICLR 2026Calibrated Information Bottleneck for Trusted Multi-modal Clustering
• CVPR 2026Beyond Whats Shared Recovering Lost Unique Information from Intermediate Layers

全部信息抽取论文

共 105 篇，第 2 / 3 页

51. CVPR 2025Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
52. CVPR 2025Relation-Rich Visual Document Generator for Visual Information Extraction
53. CVPR 2025STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds
54. CVPR 2025Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method
55. CVPR 2025Towards Source-Free Machine Unlearning
56. CVPR 2025Unified Reconstruction of Static and Dynamic Scenes from Events
57. CVPR 2024A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning
58. CVPR 2024Communication-Efficient Collaborative Perception via Information Filling with Codebook
59. CVPR 2024Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing
60. CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
61. CVPR 2024Dynamic Support Information Mining for Category-Agnostic Pose Estimation
62. CVPR 2024Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors
63. CVPR 2024Enhancing Multimodal Cooperation via Sample-level Modality Valuation
64. CVPR 2024Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields
65. CVPR 2024HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
66. CVPR 2024Improving Depth Completion via Depth Feature Upsampling
67. CVPR 2024LoS: Local Structure-Guided Stereo Matching
68. CVPR 2024LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering
69. CVPR 2024OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition
70. CVPR 2024PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar
71. CVPR 2024PolarMatte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting
72. CVPR 2024Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization
73. CVPR 2024Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion
74. CVPR 2024Seeing the World through Your Eyes
75. CVPR 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
76. CVPR 2024Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
77. CVPR 2024UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures
78. CVPR 2024Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration
79. CVPR 2023"Seeing" Electric Network Frequency From Events
80. CVPR 2023Boosting Weakly-Supervised Temporal Action Localization With Text Information
81. CVPR 2023CXTrack: Improving 3D Point Cloud Tracking With Contextual Information
82. CVPR 2023DA-DETR: Domain Adaptive Detection Transformer With Information Fusion
83. CVPR 2023Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric
84. CVPR 2023Deep Polarization Reconstruction With PDAVIS Events
85. CVPR 2023Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck
86. CVPR 2023Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition
87. CVPR 2023EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction
88. CVPR 2023Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars
89. CVPR 2023GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction
90. CVPR 2023High-Fidelity Event-Radiance Recovery via Transient Event Frequency
91. CVPR 2023HS-Pose: Hybrid Scope Feature Extraction for Category-Level Object Pose Estimation
92. CVPR 2023Invertible Neural Skinning
93. CVPR 2023JacobiNeRF: NeRF Shaping With Mutual Information Gradients
94. CVPR 2023Label Information Bottleneck for Label Enhancement
95. CVPR 2023Modeling Entities As Semantic Points for Visual Information Extraction in the Wild
96. CVPR 2023Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video
97. CVPR 2023NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud
98. CVPR 2023Occlusion-Free Scene Recovery via Neural Radiance Fields
99. CVPR 2023Polarimetric iToF: Measuring High-Fidelity Depth Through Scattering Media
100. CVPR 2023Re-Thinking Model Inversion Attacks Against Deep Neural Networks

常见问题

2023–2026 年四大会议一共有多少篇信息抽取论文？

共 798 篇，按年份分别是 2023 年 143 篇、2024 年 190 篇、2025 年 199 篇、2026 年 266 篇。

NeurIPS 2026 有多少篇信息抽取论文？

NeurIPS 2026 有 96 篇信息抽取论文，上一届是 80 篇。

ICLR 2026 有多少篇信息抽取论文？

ICLR 2026 有 63 篇信息抽取论文，上一届是 50 篇。

ICML 2026 有多少篇信息抽取论文？

ICML 2026 有 74 篇信息抽取论文，上一届是 46 篇。

CVPR 2026 有多少篇信息抽取论文？

CVPR 2026 有 33 篇信息抽取论文，上一届是 23 篇。

哪个会议的信息抽取论文最多？

NeurIPS，2023–2026 年共 287 篇。