数据集与基准论文趋势 2023–2026

新数据集与评测协议

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,856 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

数据集与基准论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023227162166382937
20244482163183641,346
20256374191893371,582
20266236352754581,991

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

全部数据集与基准论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 948 篇，第 18 / 19 页

  1. ICML 2023InfoOT: Information Maximizing Optimal Transport
  2. ICML 2023Input uncertainty propagation through trained neural networks
  3. ICML 2023Investigating the Role of Model-Based Learning in Exploration and Transfer
  4. ICML 2023Iterative Approximate Cross-Validation
  5. ICML 2023JAWS-X: Addressing Efficiency Bottlenecks of Conformal Prediction Under Standard and Feedback Covariate Shift
  6. ICML 2023Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
  7. ICML 2023Learnability and Algorithm for Continual Learning
  8. ICML 2023Learning Dense Correspondences between Photos and Sketches
  9. ICML 2023Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation
  10. ICML 2023Learning GFlowNets From Partial Episodes For Improved Convergence And Stability
  11. ICML 2023Learning Mixtures of Markov Chains and MDPs
  12. ICML 2023Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation
  13. ICML 2023Learning Prescriptive ReLU Networks
  14. ICML 2023Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning
  15. ICML 2023Learning to Boost Training by Periodic Nowcasting Near Future Weights
  16. ICML 2023LegendreTron: Uprising Proper Multiclass Loss Learning
  17. ICML 2023Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies
  18. ICML 2023Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
  19. ICML 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations
  20. ICML 2023Margin-based Neural Network Watermarking
  21. ICML 2023Measuring the Impact of Programming Language Distribution
  22. ICML 2023Mechanistic Mode Connectivity
  23. ICML 2023Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models
  24. ICML 2023Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
  25. ICML 2023Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA
  26. ICML 2023Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
  27. ICML 2023New metrics and search algorithms for weighted causal DAGs
  28. ICML 2023On the Connection Between MPNN and Graph Transformer
  29. ICML 2023On the Convergence of SARSA with Linear Function Approximation
  30. ICML 2023On the Forward Invariance of Neural ODEs
  31. ICML 2023On the Identifiability and Estimation of Causal Location-Scale Noise Models
  32. ICML 2023On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
  33. ICML 2023On the Statistical Benefits of Temporal Difference Learning
  34. ICML 2023One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training
  35. ICML 2023Optimal Arms Identification with Knapsacks
  36. ICML 2023Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
  37. ICML 2023PAC-Bayesian Offline Contextual Bandits With Guarantees
  38. ICML 2023Predicting Ordinary Differential Equations with Transformers
  39. ICML 2023Principled Offline RL in the Presence of Rich Exogenous Information
  40. ICML 2023Propensity Matters: Measuring and Enhancing Balancing for Recommendation
  41. ICML 2023ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
  42. ICML 2023Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
  43. ICML 2023Quantifying the Variability Collapse of Neural Networks
  44. ICML 2023Quantized Distributed Training of Large Models with Convergence Guarantees
  45. ICML 2023Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption
  46. ICML 2023Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework
  47. ICML 2023Reflected Diffusion Models
  48. ICML 2023Regularization-free Diffeomorphic Temporal Alignment Nets
  49. ICML 2023Regularizing Towards Soft Equivariance Under Mixed Symmetries
  50. ICML 2023Reprogramming Pretrained Language Models for Antibody Sequence Infilling

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查数据集与基准在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dataset-and-benchmarks"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「效率与系统」下的其他主题