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 266 篇，第 1 / 6 页

1. CVPR 20263D Gaussian Splatting at Arbitrary Resolutions with Compact Proxy Anchors
2. CVPR 2026ActiveGrasp Information-Guided Active Grasping with Calibrated Energy-based Model
3. CVPR 2026Aligning What Vision-Language Models See and Perceive with Adaptive Information
4. CVPR 2026BDNetBio-Inspired Dual-Backbone Small Object Detection Network
5. CVPR 2026BEA-GS BEyond RAdiance Supervision in 3DGS for Precise Object Extraction
6. CVPR 2026Beyond Whats Shared Recovering Lost Unique Information from Intermediate Layers
7. CVPR 2026CIGMA Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision
8. CVPR 2026Coded-E2LF Coded Aperture Light Field Imaging from Events
9. CVPR 2026Cross-modal Identity Mapping Minimizing Information Loss in Modality Conversion via
10. CVPR 2026Deconstructing the Failure of Ideal Noise Correction A Three-Pillar Diagnosis
11. CVPR 2026DIMOS Disentangling Instance-level Moving Object Segmentation
12. CVPR 2026Distributed Image Compression with Multimodal Side Information at Extremely Low
13. CVPR 2026End-to-End Hyper-Relational Information Extraction for Engineering Diagrams via Dynamically Tokenized
14. CVPR 2026FILTR Extracting Topological Features from Pretrained 3D Models
15. CVPR 2026From Events to Clarity The Event-Guided Diffusion Framework for Dehazing
16. CVPR 2026Global Information Thresholding for Sufficient and Necessary Circuits
17. CVPR 2026High Resolution Neural Video Coding with Bi-directional Confidence-Guided Reference Information
18. CVPR 2026IAFMNet Information-Aware Feature Modulation for Efficient Super-Resolution
19. CVPR 2026IF-Prune Information-Flow Guided Token Pruning for Efficient Vision-Language Models
20. CVPR 2026Information-Theoretic Decomposition for Multimodal Interaction Learning
21. CVPR 2026Intrinsic Concept Extraction Based on Compositional Interpretability
22. CVPR 2026Kaleidoscopic Scintillation Event Imaging
23. CVPR 2026Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
24. CVPR 2026MatE Material Extraction from Single-Image via Geometric Prior
25. CVPR 2026MODIX A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language
26. CVPR 2026PhyGaP Physically-Grounded Gaussians with Polarization Cues
27. CVPR 2026QuadSync Quadrifocal Tensor Synchronization via Tucker Decomposition
28. CVPR 2026Rethinking Glyph Spatial Information in Font Generation
29. CVPR 2026Robust Spiking Neural Networks by Temporal Mutual Information
30. CVPR 2026Scale Space Diffusion
31. CVPR 2026SeD-UD An Influence-Driven and Hierarchically-Decoupled Information Bottleneck for Multimodal Intent
32. CVPR 2026Submodel Extraction for Efficient and Personalized Federated Learning via Optimal
33. CVPR 2026TLMA Mitigating the Impact of Weakly Labeled Information for Video
34. ICLR 2026A Benchmark for Deep Information Synthesis
35. ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
36. ICLR 2026Adaptive Width Neural Networks
37. ICLR 2026Agentic Collaboration as an Information Bottleneck Problem
38. ICLR 2026An Information-Theoretic Parameter-Free Bayesian Framework for Probing Labeled Dependency Trees from Attention Score
39. ICLR 2026An Optimal Diffusion Approach to Quadratic Rate-Distortion Problems: New Solution and Approximation Methods
40. ICLR 2026Automata Learning and Identification of the Support of Language Models
41. ICLR 2026Calibrated Information Bottleneck for Trusted Multi-modal Clustering
42. ICLR 2026CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation
43. ICLR 2026COMI: Coarse-to-fine Context Compression via Marginal Information Gain
44. ICLR 2026Computational Bottlenecks for Denoising Diffusions
45. ICLR 2026Concepts' Information Bottleneck Models
46. ICLR 2026Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
47. ICLR 2026Contrastive Predictive Coding Done Right for Mutual Information Estimation
48. ICLR 2026Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence
49. ICLR 2026Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading
50. ICLR 2026Deconstructing Positional Information: From Attention Logits to Training Biases

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。