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 46 篇，第 1 / 1 页

1. ICML 2023A Picture of the Space of Typical Learnable Tasks
2. ICML 2023Abstracting Imperfect Information Away from Two-Player Zero-Sum Games
3. ICML 2023Adapting to game trees in zero-sum imperfect information games
4. ICML 2023An Information-Theoretic Analysis of Nonstationary Bandit Learning
5. ICML 2023Buying Information for Stochastic Optimization
6. ICML 2023CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design
7. ICML 2023Communication-Constrained Bandits under Additive Gaussian Noise
8. ICML 2023Continual Vision-Language Representation Learning with Off-Diagonal Information
9. ICML 2023Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets
10. ICML 2023Discrete Key-Value Bottleneck
11. ICML 2023Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost
12. ICML 2023E$(n)$ Equivariant Message Passing Simplicial Networks
13. ICML 2023Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration
14. ICML 2023Fair Neighbor Embedding
15. ICML 2023FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization
16. ICML 2023Fisher Information Embedding for Node and Graph Learning
17. ICML 2023Forget Unlearning: Towards True Data-Deletion in Machine Learning
18. ICML 2023Fundamental Tradeoffs in Learning with Prior Information
19. ICML 2023Generalization Bounds using Data-Dependent Fractal Dimensions
20. ICML 2023How Does Information Bottleneck Help Deep Learning?
21. ICML 2023Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial Information
22. ICML 2023InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models
23. ICML 2023InfoOT: Information Maximizing Optimal Transport
24. ICML 2023Inverse Reinforcement Learning without Reinforcement Learning
25. ICML 2023Learning Perturbations to Explain Time Series Predictions
26. ICML 2023Learning to Bid in Repeated First-Price Auctions with Budgets
27. ICML 2023Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model
28. ICML 2023Learning to Maximize Mutual Information for Dynamic Feature Selection
29. ICML 2023Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
30. ICML 2023Margin-based Neural Network Watermarking
31. ICML 2023Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions
32. ICML 2023Neural FIM for learning Fisher information metrics from point cloud data
33. ICML 2023Online Mechanism Design for Information Acquisition
34. ICML 2023Opponent-Limited Online Search for Imperfect Information Games
35. ICML 2023Paging with Succinct Predictions
36. ICML 2023PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation
37. ICML 2023Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision
38. ICML 2023Predicting Rare Events by Shrinking Towards Proportional Odds
39. ICML 2023Principled Offline RL in the Presence of Rich Exogenous Information
40. ICML 2023Semi-Parametric Contextual Pricing Algorithm using Cox Proportional Hazards Model
41. ICML 2023Speeding Up Bellman Ford via Minimum Violation Permutations
42. ICML 2023STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning
43. ICML 2023Tighter Information-Theoretic Generalization Bounds from Supersamples
44. ICML 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
45. ICML 2023Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features
46. ICML 2023When does Privileged information Explain Away Label Noise?

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。