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 637 篇，第 3 / 13 页

101. NeurIPS 2025CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance
102. NeurIPS 2025CogPhys: Assessing Cognitive Load via Multimodal Remote and Contact-based Physiological Sensing
103. NeurIPS 2025Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm
104. NeurIPS 2025Collaborative and Confidential Junction Trees for Hybrid Bayesian Networks
105. NeurIPS 2025ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
106. NeurIPS 2025Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms
107. NeurIPS 2025Computational Budget Should Be Considered in Data Selection
108. NeurIPS 2025ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
109. NeurIPS 2025Conditional Forecasts and Proper Scoring Rules for Reliable and Accurate Performative Predictions
110. NeurIPS 2025Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations
111. NeurIPS 2025Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning
112. NeurIPS 2025ConnectomeBench: Can LLMs proofread the connectome?
113. NeurIPS 2025ConStellaration: A dataset of QI-like stellarator plasma boundaries and optimization benchmarks
114. NeurIPS 2025Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
115. NeurIPS 2025ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
116. NeurIPS 2025CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding
117. NeurIPS 2025CoreaSpeech: Korean Speech Corpus via JAMO-based Coreset Selection for Efficient and Robust Korean Speech Generation
118. NeurIPS 2025Coreset for Robust Geometric Median: Eliminating Size Dependency on Outliers
119. NeurIPS 2025Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems
120. NeurIPS 2025CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning
121. NeurIPS 2025Cost-aware LLM-based Online Dataset Annotation
122. NeurIPS 2025Counterfactual Evolution of Multimodal Datasets via Visual Programming
123. NeurIPS 2025CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
124. NeurIPS 2025CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design
125. NeurIPS 2025CrypticBio: A Large Multimodal Dataset for Visually Confusing Species
126. NeurIPS 2025CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing
127. NeurIPS 2025CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays
128. NeurIPS 2025DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding
129. NeurIPS 2025Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models
130. NeurIPS 2025DataRater: Meta-Learned Dataset Curation
131. NeurIPS 2025Dataset Distillation of 3D Point Clouds via Distribution Matching
132. NeurIPS 2025Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality
133. NeurIPS 2025DataSIR: A Benchmark Dataset for Sensitive Information Recognition
134. NeurIPS 2025DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
135. NeurIPS 2025DAVE: Diagnostic benchmark for Audio Visual Evaluation
136. NeurIPS 2025DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection
137. NeurIPS 2025Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery
138. NeurIPS 2025DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction
139. NeurIPS 2025Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs
140. NeurIPS 2025DeltaFormer: Unlock the state space of Transformer
141. NeurIPS 2025Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
142. NeurIPS 2025Demystifying Network Foundation Models
143. NeurIPS 2025DermaCon-IN: A Multiconcept-Annotated Dermatological Image Dataset of Indian Skin Disorders for Clinical AI Research
144. NeurIPS 2025DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding
145. NeurIPS 2025DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy
146. NeurIPS 2025DGCBench: A Deep Graph Clustering Benchmark
147. NeurIPS 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
148. NeurIPS 2025Diffusion Classifiers Understand Compositionality, but Conditions Apply
149. NeurIPS 2025Diffusion Federated Dataset
150. NeurIPS 2025Dimensional Collapse in VQVAEs: Evidence and Remedies

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。