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 166 篇，第 2 / 4 页

51. ICML 2023Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs
52. ICML 2023Fisher Information Embedding for Node and Graph Learning
53. ICML 2023From Hypergraph Energy Functions to Hypergraph Neural Networks
54. ICML 2023Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods
55. ICML 2023Generalized Implicit Follow-The-Regularized-Leader
56. ICML 2023Geometric Autoencoders - What You See is What You Decode
57. ICML 2023GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
58. ICML 2023Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
59. ICML 2023Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
60. ICML 2023High Probability Convergence of Stochastic Gradient Methods
61. ICML 2023High-dimensional Clustering onto Hamiltonian Cycle
62. ICML 2023Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds
63. ICML 2023How Does Information Bottleneck Help Deep Learning?
64. ICML 2023Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning
65. ICML 2023Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
66. ICML 2023Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
67. ICML 2023Improving Fair Training under Correlation Shifts
68. ICML 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
69. ICML 2023InfoOT: Information Maximizing Optimal Transport
70. ICML 2023Input uncertainty propagation through trained neural networks
71. ICML 2023Investigating the Role of Model-Based Learning in Exploration and Transfer
72. ICML 2023Iterative Approximate Cross-Validation
73. ICML 2023JAWS-X: Addressing Efficiency Bottlenecks of Conformal Prediction Under Standard and Feedback Covariate Shift
74. ICML 2023Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
75. ICML 2023Learnability and Algorithm for Continual Learning
76. ICML 2023Learning Dense Correspondences between Photos and Sketches
77. ICML 2023Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation
78. ICML 2023Learning GFlowNets From Partial Episodes For Improved Convergence And Stability
79. ICML 2023Learning Mixtures of Markov Chains and MDPs
80. ICML 2023Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation
81. ICML 2023Learning Prescriptive ReLU Networks
82. ICML 2023Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning
83. ICML 2023Learning to Boost Training by Periodic Nowcasting Near Future Weights
84. ICML 2023LegendreTron: Uprising Proper Multiclass Loss Learning
85. ICML 2023Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies
86. ICML 2023Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
87. ICML 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations
88. ICML 2023Margin-based Neural Network Watermarking
89. ICML 2023Measuring the Impact of Programming Language Distribution
90. ICML 2023Mechanistic Mode Connectivity
91. ICML 2023Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models
92. ICML 2023Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
93. ICML 2023Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA
94. ICML 2023Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
95. ICML 2023New metrics and search algorithms for weighted causal DAGs
96. ICML 2023On the Connection Between MPNN and Graph Transformer
97. ICML 2023On the Convergence of SARSA with Linear Function Approximation
98. ICML 2023On the Forward Invariance of Neural ODEs
99. ICML 2023On the Identifiability and Estimation of Causal Location-Scale Noise Models
100. ICML 2023On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

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。