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 63 篇，第 1 / 2 页

1. ICLR 2026A Benchmark for Deep Information Synthesis
2. ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
3. ICLR 2026Adaptive Width Neural Networks
4. ICLR 2026Agentic Collaboration as an Information Bottleneck Problem
5. ICLR 2026An Information-Theoretic Parameter-Free Bayesian Framework for Probing Labeled Dependency Trees from Attention Score
6. ICLR 2026An Optimal Diffusion Approach to Quadratic Rate-Distortion Problems: New Solution and Approximation Methods
7. ICLR 2026Automata Learning and Identification of the Support of Language Models
8. ICLR 2026Calibrated Information Bottleneck for Trusted Multi-modal Clustering
9. ICLR 2026CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation
10. ICLR 2026COMI: Coarse-to-fine Context Compression via Marginal Information Gain
11. ICLR 2026Computational Bottlenecks for Denoising Diffusions
12. ICLR 2026Concepts' Information Bottleneck Models
13. ICLR 2026Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
14. ICLR 2026Contrastive Predictive Coding Done Right for Mutual Information Estimation
15. ICLR 2026Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence
16. ICLR 2026Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading
17. ICLR 2026Deconstructing Positional Information: From Attention Logits to Training Biases
18. ICLR 2026Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds
19. ICLR 2026Differentiable JPEG-based Input Perturbation for Knowledge Distillation Amplification via Conditional Mutual Information Maximization
20. ICLR 2026Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
21. ICLR 2026Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
22. ICLR 2026Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems by Exploiting Knowledge Asymmetry
23. ICLR 2026FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models
24. ICLR 2026Frequency-Balanced Retinal Representation Learning with Mutual Information Regularization
25. ICLR 2026Improving Semantic Proximity in English-Centric Information Retrieval through Cross-Lingual Alignment
26. ICLR 2026InfoBridge: Mutual Information estimation via Bridge Matching
27. ICLR 2026InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
28. ICLR 2026Information Estimation with Discrete Diffusion
29. ICLR 2026Information Shapes Koopman Representation
30. ICLR 2026Information-based Value Iteration Networks for Decision Making Under Uncertainty
31. ICLR 2026InfoScan: Information-Efficient Visual Scanning via Resource-Adaptive Walks
32. ICLR 2026InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression
33. ICLR 2026Learning a distance measure from the information-estimation geometry of data
34. ICLR 2026LiveWeb-IE: A Benchmark For Online Web Information Extraction
35. ICLR 2026Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
36. ICLR 2026Look-ahead Reasoning with a Learned Model in Imperfect Information Games
37. ICLR 2026Lossy Common Information in a Learnable Gray-Wyner Network
38. ICLR 2026Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
39. ICLR 2026Maximizing Incremental Information Entropy for Contrastive Learning
40. ICLR 2026Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
41. ICLR 2026Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information
42. ICLR 2026Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
43. ICLR 2026OrthoSolver: A Neural Proper Orthogonal Decomposition Solver For PDEs
44. ICLR 2026Pareto Variational Autoencoder
45. ICLR 2026Pseudo-Non-Linear Data Augmentation: A Constrained Energy Minimization Viewpoint
46. ICLR 2026Readout Representation: Redefining Neural Codes by Input Recovery
47. ICLR 2026RedacBench: Can AI Erase Your Secrets?
48. ICLR 2026Scaling Bayesian Experimental Design to High-Dimensions with Information-Guided Diffusion
49. ICLR 2026SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
50. ICLR 2026Sequential Information Bottleneck Fusion: Towards Robust and Generalizable Multi-Modal Brain Tumor Segmentation

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。