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 4 / 6 页

151. ICML 2026Representation Unlearning: Forgetting through Information Compression
152. ICML 2026Robust Federated Learning Against Adaptive Compression
153. ICML 2026Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment
154. ICML 2026SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
155. ICML 2026See First, Reason Later: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
156. ICML 2026SoftBinary Coding: A New Information-Theoretic Paradigm for Neural Compression via Fast Channel Simulation
157. ICML 2026Stem: Rethinking Causal Information Flow in Sparse Attention
158. ICML 2026Structure-aware Granular-Ball based Information Bottleneck for Multi-modal Clustering
159. ICML 2026SymSpectra: Symmetric Information Bottleneck Framework for Molecular Structure Recognition under Imbalanced Settings
160. ICML 2026TGPO: Efficient Policy Optimization through Sequence Anchor and Information Gating
161. ICML 2026The Cost of Information: Phase Transitions in Contextual Bandits with Paid Observations
162. ICML 2026The Entropic Signature of Class Speciation in Diffusion Models
163. ICML 2026The Information Geometry of Softmax: Probing and Steering
164. ICML 2026Tractable Expected Information Gains for Exponential Family Posteriors
165. ICML 2026UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
166. ICML 2026Uncertainty-Aware Clarification in LLM Agents with Information Gain
167. ICML 2026Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
168. ICML 2026WaterSIC: Information-Theoretically (Near) Optimal \\Linear Layer Quantization
169. ICML 2026Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL Divergences
170. ICML 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
171. NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
172. NeurIPS 2026A multi-scale information geometry reveals the structure of mutual information in neural populations
173. NeurIPS 2026A Simple Class-Agnostic Approach to Enhance Fair Adversarial Training
174. NeurIPS 2026Aggregation Dispersion: An Information-Geometric Diagnostic of Oversmoothing in Graph Neural Networks
175. NeurIPS 2026Amortized Optimal Transport from Sliced Potentials
176. NeurIPS 2026An exact information theory of generalization phase transitions in Bayesian diffusion models
177. NeurIPS 2026An Information-theoretic Framework for Auditing Unfairness in Training Data
178. NeurIPS 2026Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
179. NeurIPS 2026Behavioral Probes for Information Flow in LLM Swarms
180. NeurIPS 2026Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization
181. NeurIPS 2026Breaking Information Islands in Sparse Tuning via Small-World Connectivity
182. NeurIPS 2026CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying
183. NeurIPS 2026Can LLMs Take Retrieved Information with a Grain of Salt?
184. NeurIPS 2026CENDRe: Concept Extraction with Natural Domain Representations
185. NeurIPS 2026Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
186. NeurIPS 2026CIG: Exploration via Conditional Information Gain
187. NeurIPS 2026CLIOPATRA: Extracting Private Information from LLM Insights
188. NeurIPS 2026Conclusions from Circuit Extraction Depend on the Level of Description: A Controlled Comparison
189. NeurIPS 2026Counterfactual Predictive State Representations: The Intrinsic Dimension of Partial-Information Games
190. NeurIPS 2026CruxBench: A Benchmark of Information Discovery
191. NeurIPS 2026Does Compression Imply Generalization? A Minimum Description Length Perspective
192. NeurIPS 2026Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
193. NeurIPS 2026Exploring MLLM-Diffusion Information Transfer with MetaCanvas
194. NeurIPS 2026Extracting Training Data from Diffusion Language Models via Infilling
195. NeurIPS 2026Feature Information Dynamics in Diffusion
196. NeurIPS 2026FILOsofer: A TEE-Shielded Model Partitioning Framework based on Fisher Information-Guided LoRA Obfuscation
197. NeurIPS 2026Fine-Tuning Improves Information Conveyance in Language Models
198. NeurIPS 2026Finite-Sample and Communication-Efficient Networked Information Aggregation
199. NeurIPS 2026Fisher information and the geometry of memorization in neural networks
200. NeurIPS 2026Fisher-Glass: Tail Sample Complexity from Nuisance-Projected Fisher Information

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。