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 216 篇，第 3 / 5 页

101. ICLR 2024InstructDET: Diversifying Referring Object Detection with Generalized Instructions
102. ICLR 2024InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
103. ICLR 2024InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes
104. ICLR 2024Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
105. ICLR 2024KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval
106. ICLR 2024KoLA: Carefully Benchmarking World Knowledge of Large Language Models
107. ICLR 2024Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models
108. ICLR 2024Language Model Cascades: Token-Level Uncertainty And Beyond
109. ICLR 2024Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication
110. ICLR 2024Large Language Models Are Not Robust Multiple Choice Selectors
111. ICLR 2024Large Language Models as Automated Aligners for benchmarking Vision-Language Models
112. ICLR 2024Layer-wise linear mode connectivity
113. ICLR 2024Learning From Simplicial Data Based on Random Walks and 1D Convolutions
114. ICLR 2024Learning from Sparse Offline Datasets via Conservative Density Estimation
115. ICLR 2024Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
116. ICLR 2024Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
117. ICLR 2024Learning to Jointly Understand Visual and Tactile Signals
118. ICLR 2024Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Training Dataset
119. ICLR 2024LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
120. ICLR 2024LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
121. ICLR 2024LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
122. ICLR 2024Measuring Vision-Language STEM Skills of Neural Models
123. ICLR 2024MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
124. ICLR 2024MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
125. ICLR 2024MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
126. ICLR 2024MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations
127. ICLR 2024Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
128. ICLR 2024Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
129. ICLR 2024Momentum Benefits Non-iid Federated Learning Simply and Provably
130. ICLR 2024MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following
131. ICLR 2024Multisize Dataset Condensation
132. ICLR 2024MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
133. ICLR 2024MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
134. ICLR 2024Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace
135. ICLR 2024NEFTune: Noisy Embeddings Improve Instruction Finetuning
136. ICLR 2024Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
137. ICLR 2024Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization
138. ICLR 2024Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice
139. ICLR 2024Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
140. ICLR 2024New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
141. ICLR 2024Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
142. ICLR 2024On Harmonizing Implicit Subpopulations
143. ICLR 2024On the Joint Interaction of Models, Data, and Features
144. ICLR 2024Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
145. ICLR 2024OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
146. ICLR 2024OWL: A Large Language Model for IT Operations
147. ICLR 2024PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
148. ICLR 2024Patched Denoising Diffusion Models For High-Resolution Image Synthesis
149. ICLR 2024PeFLL: Personalized Federated Learning by Learning to Learn
150. ICLR 2024PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

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。