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 287 篇，第 2 / 6 页

51. NeurIPS 2026Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
52. NeurIPS 2026MatCurvs: Article Real-Coordinate Curve Extraction for Agent-Ready Materials Reasoning
53. NeurIPS 2026Matrix-Free Natural Gradient via Stochastic Truncated Metrics
54. NeurIPS 2026Mind the Gap: Information Disadvantage as a Learning Signal in Cooperative MARL
55. NeurIPS 2026MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation
56. NeurIPS 2026No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics
57. NeurIPS 2026On Making $SE(2)$-Invariant Networks Optimal
58. NeurIPS 2026On Minimizing Regret in Fixed-Confidence $\varepsilon$-Best Arm Identification
59. NeurIPS 2026On Reparameterizing the Score Function
60. NeurIPS 2026On the Impact of Side-Information in Bandit Learning: More is Not Always Merrier
61. NeurIPS 2026On the Information Loss of Multi-Token Prediction: Origin and Solution
62. NeurIPS 2026Opening the Black Box of Classifier-Free Guidance via Information Bottleneck
63. NeurIPS 2026PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting
64. NeurIPS 2026PANDA: Prior-guided Attentional Dual-path Architecture
65. NeurIPS 2026PatchScout: Thematic Web Data Collection via Information Foraging
66. NeurIPS 2026Pathways of Visual Information Flow in Vision-Language Models
67. NeurIPS 2026PepDDG: Peptide–Protein Binding ΔΔ𝐺 Prediction via Information Channel Decomposition
68. NeurIPS 2026PLACE: Patch-Level Agnostic Concept Extraction
69. NeurIPS 2026PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization
70. NeurIPS 2026Reading Positional Coupling in Transformers with Diffusion Scores
71. NeurIPS 2026Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
72. NeurIPS 2026Refinement as a Service: Algorithmic Predictor Refinement
73. NeurIPS 2026Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
74. NeurIPS 2026Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
75. NeurIPS 2026Robust Multi-view Clustering against Imperfect Information
76. NeurIPS 2026SAME: Stability-Aware Embedding Extraction in Mixture-of-Experts Language Models
77. NeurIPS 2026SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information
78. NeurIPS 2026Securing AI Agents with Information-Flow Control
79. NeurIPS 2026Self-Distilled RLVR
80. NeurIPS 2026Selling Information While Being an Interested Party
81. NeurIPS 2026SPATIALEPIBENCH: Benchmarking Spatial Information and Epidemic Priors in Forecasting
82. NeurIPS 2026Spectral Estimation with Deformed Decompression
83. NeurIPS 2026Spectral Geometry of Attention: From Information Routing to Uncertainty
84. NeurIPS 2026Stabilizing RL+Search for Imperfect-Information Extensive-Form Games
85. NeurIPS 2026Submodular Benchmark Selection
86. NeurIPS 2026The Bayesian Learning Rule Beyond KL Geometry
87. NeurIPS 2026The Communication Bottleneck: A Round-Trip Study of Compositional Serialization in Language Models
88. NeurIPS 2026The limbic navigation system as a hierarchical RNN
89. NeurIPS 2026The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval
90. NeurIPS 2026The Type Theory of Stationary MDPs: Rare Events and Uncertainty Quantification
91. NeurIPS 2026Theoretical Limits of Language Model Alignment
92. NeurIPS 2026TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
93. NeurIPS 2026Training Language Models to Explain Their Own Computations
94. NeurIPS 2026Transfer Entropy as a Measure of Information Flow in VLMs and LLMs
95. NeurIPS 2026Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
96. NeurIPS 2026Why Cancer cfDNA Models Fail on Chronic Disease: A Geometric Information-Theoretic Bound and Its Architectural Implications
97. NeurIPS 2025A Pre-training Framework for Relational Data with Information-theoretic Principles
98. NeurIPS 2025A Semantic Parsing Framework for End-to-End Time Normalization
99. NeurIPS 2025Balanced Active Inference
100. NeurIPS 2025ChemX: A Collection of Chemistry Datasets for Benchmarking Automated Information Extraction

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。