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 199 篇，第 2 / 4 页

51. ICLR 2025Inner Information Analysis Algorithm for Deep Neural Network based on Community
52. ICLR 2025Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck
53. ICLR 2025Laplace Sample Information: Data Informativeness Through a Bayesian Lens
54. ICLR 2025Learning Robust Representations with Long-Term Information for Generalization in Visual Reinforcement Learning
55. ICLR 2025Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
56. ICLR 2025MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
57. ICLR 2025Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
58. ICLR 2025Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization
59. ICLR 2025On Bits and Bandits: Quantifying the Regret-Information Trade-off
60. ICLR 2025On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions
61. ICLR 2025On the Relation between Trainability and Dequantization of Variational Quantum Learning Models
62. ICLR 2025Projection Head is Secretly an Information Bottleneck
63. ICLR 2025Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
64. ICLR 2025Scalable Extraction of Training Data from Aligned, Production Language Models
65. ICLR 2025Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods
66. ICLR 2025Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
67. ICLR 2025Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning
68. ICLR 2025The Value of Sensory Information to a Robot
69. ICLR 2025TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
70. ICLR 2025Transformer Meets Twicing: Harnessing Unattended Residual Information
71. ICLR 2025UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models
72. ICLR 2025VoxDialogue: Can Spoken Dialogue Systems Understand Information Beyond Words?
73. ICLR 2025What should a neuron aim for? Designing local objective functions based on information theory
74. ICML 2025A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method
75. ICML 2025A Theoretical Justification for Asymmetric Actor-Critic Algorithms
76. ICML 2025A Variational Information Theoretic Approach to Out-of-Distribution Detection
77. ICML 2025Adaptive Elicitation of Latent Information Using Natural Language
78. ICML 2025Aligning Multimodal Representations through an Information Bottleneck
79. ICML 2025An Effective and Secure Federated Multi-View Clustering Method with Information-Theoretic Perspective
80. ICML 2025An Efficient Search-and-Score Algorithm for Ancestral Graphs using Multivariate Information Scores for Complex Non-linear and Categorical Data
81. ICML 2025CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
82. ICML 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
83. ICML 2025Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation
84. ICML 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
85. ICML 2025De-mark: Watermark Removal in Large Language Models
86. ICML 2025DeepCrossAttention: Supercharging Transformer Residual Connections
87. ICML 2025Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
88. ICML 2025DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
89. ICML 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
90. ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
91. ICML 2025Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
92. ICML 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
93. ICML 2025Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
94. ICML 2025FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
95. ICML 2025Fragments to Facts: Partial-Information Fragment Inference from LLMs
96. ICML 2025Functional Alignment Can Mislead: Examining Model Stitching
97. ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
98. ICML 2025Graph4MM: Weaving Multimodal Learning with Structural Information
99. ICML 2025Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting
100. ICML 2025Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback

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。