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 5,852 篇，第 3 / 118 页

101. CVPR 2026DROID-SLAM in the Wild
102. CVPR 2026Dual-Estimator Decoupling Global and Local Semantic Shift for Drift Compensation
103. CVPR 2026Duala Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI
104. CVPR 2026DuetMerging Synergizing Dynamic and Static Strategies for Mitigating Task Interference
105. CVPR 2026Dynamic Label Noise Suppression with Optimal Teacher Pool for Facial
106. CVPR 2026E-comIQ-ZH A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of
107. CVPR 2026E2-SCI Elastic Edge-Cloud Speculative Decoding via Credit Inertia
108. CVPR 2026Ego-InBetween Generating Object State Transitions in Ego-Centric Videos
109. CVPR 2026EgoEdit Dataset Real-Time Streaming Model and Benchmark for Egocentric Video
110. CVPR 2026EgoXtreme A Dataset for Robust Object Pose Estimation in Egocentric
111. CVPR 2026EmoThinker Advancing Visual-Acoustic Emotion Analysis via Structural Token Selection and
112. CVPR 2026EnergyAction Unimanual to Bimanual Composition with Energy-Based Models
113. CVPR 2026Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands
114. CVPR 2026Event Stream Filtering via Probability Flux Estimation
115. CVPR 2026Event Structural Valley A Unified Theoretical and Practical Framework for
116. CVPR 2026Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset
117. CVPR 2026Event6D Event-based Novel Object 6D Pose Tracking
118. CVPR 2026EventGait Towards Robust Gait Recognition with Event Streams
119. CVPR 2026Evidential Deep Partial Label Learning to Quantify Disambiguation Uncertainty
120. CVPR 2026Evidential Neural Radiance Fields
121. CVPR 2026Exact-GS Mathematically Rigorous and Accurate 3D Gaussian Splatting for 3D
122. CVPR 2026Exemplar-Free Class Incremental Learning via Preserving Class-Discriminative Structure
123. CVPR 2026Expanding mmWave Datasets for Human Pose Estimation with Unlabeled Data
124. CVPR 2026Exploring Spatial Intelligence from a Generative Perspective
125. CVPR 2026Exposing and Evaluating Hallucinations for GUI Grounding
126. CVPR 2026Extending Embodied Question Answering from Perception to Decision
127. CVPR 2026F2HDR Two-Stage HDR Video Reconstruction via Flow Adapter and Physical
128. CVPR 2026FACE A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh
129. CVPR 2026FailureAtlas Mapping the Failure Landscape of T2I Models via Active
130. CVPR 2026Fast SceneScript Fast and Accurate Language-Based 3D Scene Understanding via
131. CVPR 2026FastGS Training 3D Gaussian Splatting in 100 Seconds
132. CVPR 2026FE2E From Editor to Dense Geometry Estimator
133. CVPR 2026Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
134. CVPR 2026FedSDR Federated Graph Learning with Structural Noise Detection and Reconstruction
135. CVPR 2026Few-Shot Hybrid Incremental LearningContinually Learning under Data Scarcity and Task
136. CVPR 2026FHAvatar Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head
137. CVPR 2026Fighting Hallucinations with Counterfactuals Diffusion-Guided Perturbations for LVLM Hallucination Suppression
138. CVPR 2026FilterGS Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD
139. CVPR 2026FinPercep-RM A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based
140. CVPR 2026FlashCap Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based
141. CVPR 2026FlexAvatar Learning Complete 3D Head Avatars with Partial Supervision
142. CVPR 2026FlowFM Advancing Dark Optical Flow Estimation with Flow Matching
143. CVPR 2026FMPose3D monocular 3D pose estimation via flow matching
144. CVPR 2026FoV-Net Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
145. CVPR 2026FreeArtGS Articulated Gaussian Splatting Under Free-moving Scenario
146. CVPR 2026From Measurement to Mitigation Quantifying and Reducing Identity Leakage in
147. CVPR 2026FSFSplatter Geometrically Accurate Reconstruction with Free Sparse-view Images within 2
148. CVPR 2026Fully Decentralized Certified Unlearning
149. CVPR 2026FUN REC Reconstructing Functional 3D Scenes from Egocentric Interaction
150. CVPR 2026Fusion of Depth and Semantics for Probabilistic Floorplan Localization

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。