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 143 篇，第 3 / 3 页

101. NeurIPS 2023A unified framework for information-theoretic generalization bounds
102. NeurIPS 2023An information-theoretic quantification of the content of communication between brain regions
103. NeurIPS 2023Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits
104. NeurIPS 2023AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web
105. NeurIPS 2023Data Pruning via Moving-one-Sample-out
106. NeurIPS 2023Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training
107. NeurIPS 2023Easy Learning from Label Proportions
108. NeurIPS 2023Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
109. NeurIPS 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Values
110. NeurIPS 2023FairLISA: Fair User Modeling with Limited Sensitive Attributes Information
111. NeurIPS 2023Faster Relative Entropy Coding with Greedy Rejection Coding
112. NeurIPS 2023Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts
113. NeurIPS 2023Gacs-Korner Common Information Variational Autoencoder
114. NeurIPS 2023Generalized Information-theoretic Multi-view Clustering
115. NeurIPS 2023Group Robust Classification Without Any Group Information
116. NeurIPS 2023Ignorance is Bliss: Robust Control via Information Gating
117. NeurIPS 2023Improving Adversarial Robustness via Information Bottleneck Distillation
118. NeurIPS 2023InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
119. NeurIPS 2023Information Geometry of the Retinal Representation Manifold
120. NeurIPS 2023Information Theoretic Lower Bounds for Information Theoretic Upper Bounds
121. NeurIPS 2023Information-guided Planning: An Online Approach for Partially Observable Problems
122. NeurIPS 2023Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization
123. NeurIPS 2023Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts
124. NeurIPS 2023K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing
125. NeurIPS 2023Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information
126. NeurIPS 2023Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack
127. NeurIPS 2023Max-Sliced Mutual Information
128. NeurIPS 2023MIM4DD: Mutual Information Maximization for Dataset Distillation
129. NeurIPS 2023OceanBench: The Sea Surface Height Edition
130. NeurIPS 2023On quantum backpropagation, information reuse, and cheating measurement collapse
131. NeurIPS 2023On Slicing Optimality for Mutual Information
132. NeurIPS 2023Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting
133. NeurIPS 2023PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
134. NeurIPS 2023Reinforcement Learning with Simple Sequence Priors
135. NeurIPS 2023Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds
136. NeurIPS 2023The Bayesian Stability Zoo
137. NeurIPS 2023Time-Independent Information-Theoretic Generalization Bounds for SGLD
138. NeurIPS 2023Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
139. NeurIPS 2023Unified Lower Bounds for Interactive High-dimensional Estimation under Information Constraints
140. NeurIPS 2023Unsupervised Behavior Extraction via Random Intent Priors
141. NeurIPS 2023When can Regression-Adjusted Control Variate Help? Rare Events, Sobolev Embedding and Minimax Optimality
142. NeurIPS 2023WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting
143. NeurIPS 2023XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary 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。