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 231 篇，第 2 / 5 页

51. ICML 2026Provable Accuracy Collapse of Embedding-Based Representations under Dimensionality Mismatch
52. ICML 2026Provably Learning Attention with Queries
53. ICML 2026Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
54. ICML 2026Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
55. ICML 2026Representation Unlearning: Forgetting through Information Compression
56. ICML 2026Robust Federated Learning Against Adaptive Compression
57. ICML 2026Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment
58. ICML 2026SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
59. ICML 2026See First, Reason Later: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
60. ICML 2026SoftBinary Coding: A New Information-Theoretic Paradigm for Neural Compression via Fast Channel Simulation
61. ICML 2026Stem: Rethinking Causal Information Flow in Sparse Attention
62. ICML 2026Structure-aware Granular-Ball based Information Bottleneck for Multi-modal Clustering
63. ICML 2026SymSpectra: Symmetric Information Bottleneck Framework for Molecular Structure Recognition under Imbalanced Settings
64. ICML 2026TGPO: Efficient Policy Optimization through Sequence Anchor and Information Gating
65. ICML 2026The Cost of Information: Phase Transitions in Contextual Bandits with Paid Observations
66. ICML 2026The Entropic Signature of Class Speciation in Diffusion Models
67. ICML 2026The Information Geometry of Softmax: Probing and Steering
68. ICML 2026Tractable Expected Information Gains for Exponential Family Posteriors
69. ICML 2026UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
70. ICML 2026Uncertainty-Aware Clarification in LLM Agents with Information Gain
71. ICML 2026Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
72. ICML 2026WaterSIC: Information-Theoretically (Near) Optimal \\Linear Layer Quantization
73. ICML 2026Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL Divergences
74. ICML 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
75. ICML 2025A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method
76. ICML 2025A Theoretical Justification for Asymmetric Actor-Critic Algorithms
77. ICML 2025A Variational Information Theoretic Approach to Out-of-Distribution Detection
78. ICML 2025Adaptive Elicitation of Latent Information Using Natural Language
79. ICML 2025Aligning Multimodal Representations through an Information Bottleneck
80. ICML 2025An Effective and Secure Federated Multi-View Clustering Method with Information-Theoretic Perspective
81. ICML 2025An Efficient Search-and-Score Algorithm for Ancestral Graphs using Multivariate Information Scores for Complex Non-linear and Categorical Data
82. ICML 2025CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
83. ICML 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
84. ICML 2025Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation
85. ICML 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
86. ICML 2025De-mark: Watermark Removal in Large Language Models
87. ICML 2025DeepCrossAttention: Supercharging Transformer Residual Connections
88. ICML 2025Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
89. ICML 2025DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
90. ICML 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
91. ICML 2025Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
92. ICML 2025Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
93. ICML 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
94. ICML 2025Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
95. ICML 2025FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
96. ICML 2025Fragments to Facts: Partial-Information Fragment Inference from LLMs
97. ICML 2025Functional Alignment Can Mislead: Examining Model Stitching
98. ICML 2025Generalization in Federated Learning: A Conditional Mutual Information Framework
99. ICML 2025Graph4MM: Weaving Multimodal Learning with Structural Information
100. ICML 2025Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting

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。