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 190 篇，第 1 / 4 页

1. CVPR 2024A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning
2. CVPR 2024Communication-Efficient Collaborative Perception via Information Filling with Codebook
3. CVPR 2024Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing
4. CVPR 2024Differentiable Information Bottleneck for Deterministic Multi-view Clustering
5. CVPR 2024Dynamic Support Information Mining for Category-Agnostic Pose Estimation
6. CVPR 2024Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors
7. CVPR 2024Enhancing Multimodal Cooperation via Sample-level Modality Valuation
8. CVPR 2024Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields
9. CVPR 2024HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
10. CVPR 2024Improving Depth Completion via Depth Feature Upsampling
11. CVPR 2024LoS: Local Structure-Guided Stereo Matching
12. CVPR 2024LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering
13. CVPR 2024OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition
14. CVPR 2024PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar
15. CVPR 2024PolarMatte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting
16. CVPR 2024Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization
17. CVPR 2024Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion
18. CVPR 2024Seeing the World through Your Eyes
19. CVPR 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
20. CVPR 2024Time-Efficient Light-Field Acquisition Using Coded Aperture and Events
21. CVPR 2024UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures
22. CVPR 2024Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration
23. ICLR 2024A Mutual Information Perspective on Federated Contrastive Learning
24. ICLR 2024Augmenting Transformers with Recursively Composed Multi-grained Representations
25. ICLR 2024Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
26. ICLR 2024Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification
27. ICLR 2024Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
28. ICLR 2024Cauchy-Schwarz Divergence Information Bottleneck for Regression
29. ICLR 2024CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
30. ICLR 2024Conditional Information Bottleneck Approach for Time Series Imputation
31. ICLR 2024Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
32. ICLR 2024Dynamic Discounted Counterfactual Regret Minimization
33. ICLR 2024Dynamic Neural Response Tuning
34. ICLR 2024Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
35. ICLR 2024Entropy Coding of Unordered Data Structures
36. ICLR 2024Estimating Conditional Mutual Information for Dynamic Feature Selection
37. ICLR 2024Faithful Rule Extraction for Differentiable Rule Learning Models
38. ICLR 2024GeoLLM: Extracting Geospatial Knowledge from Large Language Models
39. ICLR 2024GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
40. ICLR 2024Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
41. ICLR 2024Information Retention via Learning Supplemental Features
42. ICLR 2024Interpretable Diffusion via Information Decomposition
43. ICLR 2024Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
44. ICLR 2024Leave-one-out Distinguishability in Machine Learning
45. ICLR 2024Meta-Learning Priors Using Unrolled Proximal Networks
46. ICLR 2024MINDE: Mutual Information Neural Diffusion Estimation
47. ICLR 2024NetInfoF Framework: Measuring and Exploiting Network Usable Information
48. ICLR 2024Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
49. ICLR 2024Nougat: Neural Optical Understanding for Academic Documents
50. ICLR 2024Online Information Acquisition: Hiring Multiple Agents

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。