数据集与基准论文趋势 2023–2026

主要结论

• 数据集与基准论文从 2023 年的 937 篇增长到 2026 年的 1,991 篇，三年间扩大到约 2.1 倍。
• NeurIPS 是发数据集与基准论文最多的会议，2023–2026 年共 1,935 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 8 篇增至 2026 年的 194 篇。
• 在「效率与系统」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的硬件协同是 4.4 倍，数据集与基准是 2.1 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 2026A Surrogate Perspective on Convergence of Fixed-Target DQN
• ICML 2026$\mu$pscaling small models: Principled warm starts and hyperparameter transfer
• ICLR 2026**TandemFoilSet**: Datasets for Flow Field Prediction of Tandem-Airfoil Through the Reuse of Single Airfoils
• CVPR 20264DEquine Disentangling Motion and Appearance for 4D Equine Reconstruction from
• NeurIPS 2025A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
• ICML 2025Active Evaluation Acquisition for Efficient LLM Benchmarking
• ICLR 2025$F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
• CVPR 20253D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
• NeurIPS 2024A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions
• ICML 2024A connection between Tempering and Entropic Mirror Descent
• ICLR 2024A Benchmark Study on Calibration
• CVPR 2024Data Valuation and Detections in Federated Learning
• NeurIPS 2023$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties
• ICML 2023A Picture of the Space of Typical Learnable Tasks
• ICLR 2023$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
• CVPR 2023A Bag-of-Prototypes Representation for Dataset-Level Applications
• NeurIPS 2026A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning
• ICML 2026A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation
• ICLR 2026A Fictional Q&A Dataset for Studying Memorization and Knowledge Acquisition
• CVPR 2026Advancing Cancer Prognosis with Hierarchical Fusion of Genomic Proteomic and

全部数据集与基准论文

共 318 篇，第 3 / 7 页

101. ICML 2024Evaluation of Test-Time Adaptation Under Computational Time Constraints
102. ICML 2024Expressivity and Generalization: Fragment-Biases for Molecular GNNs
103. ICML 2024Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
104. ICML 2024Faithfulness Measurable Masked Language Models
105. ICML 2024Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
106. ICML 2024Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
107. ICML 2024Fine-grained Classes and How to Find Them
108. ICML 2024Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention
109. ICML 2024FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
110. ICML 2024Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
111. ICML 2024GATE: How to Keep Out Intrusive Neighbors
112. ICML 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagation
113. ICML 2024Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
114. ICML 2024Generalization to New Sequential Decision Making Tasks with In-Context Learning
115. ICML 2024GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
116. ICML 2024Graph Out-of-Distribution Detection Goes Neighborhood Shaping
117. ICML 2024Graph Positional and Structural Encoder
118. ICML 2024GroupCover: A Secure, Efficient and Scalable Inference Framework for On-device Model Protection based on TEEs
119. ICML 2024Handling Heterogeneous Curvatures in Bandit LQR Control
120. ICML 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
121. ICML 2024Harmonizing Generalization and Personalization in Federated Prompt Learning
122. ICML 2024Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
123. ICML 2024Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning
124. ICML 2024Hierarchical Integral Probability Metrics: A distance on random probability measures with low sample complexity
125. ICML 2024How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
126. ICML 2024How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
127. ICML 2024How Spurious Features are Memorized: Precise Analysis for Random and NTK Features
128. ICML 2024How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
129. ICML 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis
130. ICML 2024Hybrid Reinforcement Learning from Offline Observation Alone
131. ICML 2024Identification and Estimation for Nonignorable Missing Data: A Data Fusion Approach
132. ICML 2024Imitation Learning in Discounted Linear MDPs without exploration assumptions
133. ICML 2024Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
134. ICML 2024Improved Modelling of Federated Datasets using Mixtures-of-Dirichlet-Multinomials
135. ICML 2024Improved Operator Learning by Orthogonal Attention
136. ICML 2024Improving Antibody Humanness Prediction using Patent Data
137. ICML 2024Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
138. ICML 2024Improving Sharpness-Aware Minimization by Lookahead
139. ICML 2024In-Context Language Learning: Architectures and Algorithms
140. ICML 2024In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
141. ICML 2024Incremental Topological Ordering and Cycle Detection with Predictions
142. ICML 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
143. ICML 2024Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks
144. ICML 2024Initial Guessing Bias: How Untrained Networks Favor Some Classes
145. ICML 2024Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment
146. ICML 2024InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
147. ICML 2024Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification
148. ICML 2024Interpreting and Improving Diffusion Models from an Optimization Perspective
149. ICML 2024Interpreting and Improving Large Language Models in Arithmetic Calculation
150. ICML 2024Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs

常见问题

2023–2026 年四大会议一共有多少篇数据集与基准论文？

共 5,856 篇，按年份分别是 2023 年 937 篇、2024 年 1,346 篇、2025 年 1,582 篇、2026 年 1,991 篇。

NeurIPS 2026 有多少篇数据集与基准论文？

NeurIPS 2026 有 623 篇数据集与基准论文，上一届是 637 篇。

ICLR 2026 有多少篇数据集与基准论文？

ICLR 2026 有 635 篇数据集与基准论文，上一届是 419 篇。

ICML 2026 有多少篇数据集与基准论文？

ICML 2026 有 275 篇数据集与基准论文，上一届是 189 篇。

CVPR 2026 有多少篇数据集与基准论文？

CVPR 2026 有 458 篇数据集与基准论文，上一届是 337 篇。

哪个会议的数据集与基准论文最多？

NeurIPS，2023–2026 年共 1,935 篇。