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 798 篇，第 2 / 16 页

51. ICLR 2026Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds
52. ICLR 2026Differentiable JPEG-based Input Perturbation for Knowledge Distillation Amplification via Conditional Mutual Information Maximization
53. ICLR 2026Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
54. ICLR 2026Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
55. ICLR 2026Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems by Exploiting Knowledge Asymmetry
56. ICLR 2026FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models
57. ICLR 2026Frequency-Balanced Retinal Representation Learning with Mutual Information Regularization
58. ICLR 2026Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual Alignment
59. ICLR 2026InfoBridge: Mutual Information estimation via Bridge Matching
60. ICLR 2026InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
61. ICLR 2026Information Estimation with Discrete Diffusion
62. ICLR 2026Information Shapes Koopman Representation
63. ICLR 2026Information-based Value Iteration Networks for Decision Making Under Uncertainty
64. ICLR 2026InfoScan: Information-Efficient Visual Scanning via Resource-Adaptive Walks
65. ICLR 2026InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression
66. ICLR 2026Learning a distance measure from the information-estimation geometry of data
67. ICLR 2026LiveWeb-IE: A Benchmark For Online Web Information Extraction
68. ICLR 2026Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
69. ICLR 2026Look-ahead Reasoning with a Learned Model in Imperfect Information Games
70. ICLR 2026Lossy Common Information in a Learnable Gray-Wyner Network
71. ICLR 2026Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
72. ICLR 2026Maximizing Incremental Information Entropy for Contrastive Learning
73. ICLR 2026Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
74. ICLR 2026Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information
75. ICLR 2026Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
76. ICLR 2026OrthoSolver: A Neural Proper Orthogonal Decomposition Solver For PDEs
77. ICLR 2026Pareto Variational Autoencoder
78. ICLR 2026Pseudo-Non-Linear Data Augmentation: A Constrained Energy Minimization Viewpoint
79. ICLR 2026Readout Representation: Redefining Neural Codes by Input Recovery
80. ICLR 2026RedacBench: Can AI Erase Your Secrets?
81. ICLR 2026Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided Diffusion
82. ICLR 2026SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
83. ICLR 2026Sequential Information Bottleneck Fusion: Towards Robust and Generalizable Multi-Modal Brain Tumor Segmentation
84. ICLR 2026SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video Diffusion
85. ICLR 2026SPICE: Submodular Penalized Information–Conflict Selection for Efficient Large Language Model Training
86. ICLR 2026The Spacetime of Diffusion Models: An Information Geometry Perspective
87. ICLR 2026The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
88. ICLR 2026The Value of Information in Human-AI Decision-making
89. ICLR 2026There Was Never a Bottleneck in Concept Bottleneck Models
90. ICLR 2026To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
91. ICLR 2026Toward Principled Flexible Scaling for Self-Gated Neural Activation
92. ICLR 2026Towards Strategic Persuasion with Language Models
93. ICLR 2026Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusion
94. ICLR 2026Using maximal information auxiliary variables to improve synthetic data generation based on TabPFN foundation models
95. ICLR 2026What matters for Representation Alignment: Global Information or Spatial Structure?
96. ICLR 2026Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
97. ICML 2026$\alpha$-PFN: Fast Entropy Search via In-Context Learning
98. ICML 2026A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
99. ICML 2026AD-BTS: Adaptive Dual-Branch Token Sparsification via Spatial Information Density
100. ICML 2026Approximating Drift-Diffusion Models for User Decisions under Nudging and External Information

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。