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 5,852 篇，第 111 / 118 页

  1. ICML 2023Evaluating Unsupervised Denoising Requires Unsupervised Metrics
  2. ICML 2023Explainability as statistical inference
  3. ICML 2023Exploring the Benefits of Training Expert Language Models over Instruction Tuning
  4. ICML 2023Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
  5. ICML 2023Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms
  6. ICML 2023Fair and Optimal Classification via Post-Processing
  7. ICML 2023Fast Excess Risk Rates via Offset Rademacher Complexity
  8. ICML 2023Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
  9. ICML 2023Finding Generalization Measures by Contrasting Signal and Noise
  10. ICML 2023Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs
  11. ICML 2023Fisher Information Embedding for Node and Graph Learning
  12. ICML 2023From Hypergraph Energy Functions to Hypergraph Neural Networks
  13. ICML 2023Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods
  14. ICML 2023Generalized Implicit Follow-The-Regularized-Leader
  15. ICML 2023Geometric Autoencoders - What You See is What You Decode
  16. ICML 2023GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
  17. ICML 2023Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
  18. ICML 2023Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
  19. ICML 2023High Probability Convergence of Stochastic Gradient Methods
  20. ICML 2023High-dimensional Clustering onto Hamiltonian Cycle
  21. ICML 2023Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds
  22. ICML 2023How Does Information Bottleneck Help Deep Learning?
  23. ICML 2023Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning
  24. ICML 2023Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
  25. ICML 2023Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
  26. ICML 2023Improving Fair Training under Correlation Shifts
  27. ICML 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
  28. ICML 2023InfoOT: Information Maximizing Optimal Transport
  29. ICML 2023Input uncertainty propagation through trained neural networks
  30. ICML 2023Investigating the Role of Model-Based Learning in Exploration and Transfer
  31. ICML 2023Iterative Approximate Cross-Validation
  32. ICML 2023JAWS-X: Addressing Efficiency Bottlenecks of Conformal Prediction Under Standard and Feedback Covariate Shift
  33. ICML 2023Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
  34. ICML 2023Learnability and Algorithm for Continual Learning
  35. ICML 2023Learning Dense Correspondences between Photos and Sketches
  36. ICML 2023Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation
  37. ICML 2023Learning GFlowNets From Partial Episodes For Improved Convergence And Stability
  38. ICML 2023Learning Mixtures of Markov Chains and MDPs
  39. ICML 2023Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation
  40. ICML 2023Learning Prescriptive ReLU Networks
  41. ICML 2023Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning
  42. ICML 2023Learning to Boost Training by Periodic Nowcasting Near Future Weights
  43. ICML 2023LegendreTron: Uprising Proper Multiclass Loss Learning
  44. ICML 2023Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies
  45. ICML 2023Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
  46. ICML 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations
  47. ICML 2023Margin-based Neural Network Watermarking
  48. ICML 2023Measuring the Impact of Programming Language Distribution
  49. ICML 2023Mechanistic Mode Connectivity
  50. ICML 2023Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models

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