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 227 篇，第 2 / 5 页

51. NeurIPS 2023DataPerf: Benchmarks for Data-Centric AI Development
52. NeurIPS 2023Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations
53. NeurIPS 2023Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
54. NeurIPS 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
55. NeurIPS 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safety
56. NeurIPS 2023Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
57. NeurIPS 2023Diverse Community Data for Benchmarking Data Privacy Algorithms
58. NeurIPS 2023Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework
59. NeurIPS 2023Domain Agnostic Fourier Neural Operators
60. NeurIPS 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
61. NeurIPS 2023Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
62. NeurIPS 2023Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
63. NeurIPS 2023Dream the Impossible: Outlier Imagination with Diffusion Models
64. NeurIPS 2023DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening
65. NeurIPS 2023ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram
66. NeurIPS 2023Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks
67. NeurIPS 2023Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks
68. NeurIPS 2023EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset
69. NeurIPS 2023EPIC Fields: Marrying 3D Geometry and Video Understanding
70. NeurIPS 2023Estimating Generic 3D Room Structures from 2D Annotations
71. NeurIPS 2023EV-Eye: Rethinking High-frequency Eye Tracking through the Lenses of Event Cameras
72. NeurIPS 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
73. NeurIPS 2023Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts
74. NeurIPS 2023Expanding Small-Scale Datasets with Guided Imagination
75. NeurIPS 2023Fast and Simple Spectral Clustering in Theory and Practice
76. NeurIPS 2023FAST: a Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects Estimation
77. NeurIPS 2023FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
78. NeurIPS 2023FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
79. NeurIPS 2023Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
80. NeurIPS 2023Frequency Domain-Based Dataset Distillation
81. NeurIPS 2023Gacs-Korner Common Information Variational Autoencoder
82. NeurIPS 2023GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition
83. NeurIPS 2023GMSF: Global Matching Scene Flow
84. NeurIPS 2023GPEX, A Framework For Interpreting Artificial Neural Networks
85. NeurIPS 2023GSLB: The Graph Structure Learning Benchmark
86. NeurIPS 2023H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets
87. NeurIPS 2023Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
88. NeurIPS 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
89. NeurIPS 2023How hard are computer vision datasets? Calibrating dataset difficulty to viewing time
90. NeurIPS 2023HT-Step: Aligning Instructional Articles with How-To Videos
91. NeurIPS 2023Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context
92. NeurIPS 2023Hyper-HMM: aligning human brains and semantic features in a common latent event space
93. NeurIPS 2023Hyper-Skin: A Hyperspectral Dataset for Reconstructing Facial Skin-Spectra from RGB Images
94. NeurIPS 2023ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets
95. NeurIPS 2023Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
96. NeurIPS 2023Improving multimodal datasets with image captioning
97. NeurIPS 2023Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks
98. NeurIPS 2023INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis
99. NeurIPS 2023Into the LAION’s Den: Investigating Hate in Multimodal Datasets
100. NeurIPS 2023Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy

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。