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 110 / 118 页

  1. ICLR 2023Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
  2. ICLR 2023What Can we Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers?
  3. ICLR 2023What Is Missing in IRM Training and Evaluation? Challenges and Solutions
  4. ICLR 2023What learning algorithm is in-context learning? Investigations with linear models
  5. ICLR 2023When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?
  6. ICLR 2023When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
  7. ICLR 2023When to Make and Break Commitments?
  8. ICLR 2023Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions
  9. ICLR 2023WikiWhy: Answering and Explaining Cause-and-Effect Questions
  10. ICML 2023A Flexible Diffusion Model
  11. ICML 2023A Generalization of ViT/MLP-Mixer to Graphs
  12. ICML 2023A New PHO-rmula for Improved Performance of Semi-Structured Networks
  13. ICML 2023A Picture of the Space of Typical Learnable Tasks
  14. ICML 2023A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
  15. ICML 2023A Study on Transformer Configuration and Training Objective
  16. ICML 2023Achieving Linear Speedup in Non-IID Federated Bilevel Learning
  17. ICML 2023Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
  18. ICML 2023An Effective Meaningful Way to Evaluate Survival Models
  19. ICML 2023Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation
  20. ICML 2023Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
  21. ICML 2023Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.
  22. ICML 2023Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?
  23. ICML 2023Atari-5: Distilling the Arcade Learning Environment down to Five Games
  24. ICML 2023Automatic Data Augmentation via Invariance-Constrained Learning
  25. ICML 2023Auxiliary Learning as an Asymmetric Bargaining Game
  26. ICML 2023Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
  27. ICML 2023Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies
  28. ICML 2023Bootstrap in High Dimension with Low Computation
  29. ICML 2023Can Neural Network Memorization Be Localized?
  30. ICML 2023Change is Hard: A Closer Look at Subpopulation Shift
  31. ICML 2023Cluster Explanation via Polyhedral Descriptions
  32. ICML 2023ClusterFuG: Clustering Fully connected Graphs by Multicut
  33. ICML 2023Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation
  34. ICML 2023Consistency of Multiple Kernel Clustering
  35. ICML 2023Contextual Combinatorial Bandits with Probabilistically Triggered Arms
  36. ICML 2023Contextual Reliability: When Different Features Matter in Different Contexts
  37. ICML 2023Cross-Modal Fine-Tuning: Align then Refine
  38. ICML 2023CrossSplit: Mitigating Label Noise Memorization through Data Splitting
  39. ICML 2023Data Feedback Loops: Model-driven Amplification of Dataset Biases
  40. ICML 2023Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value
  41. ICML 2023Dataset Distillation with Convexified Implicit Gradients
  42. ICML 2023Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
  43. ICML 2023Decoding Layer Saliency in Language Transformers
  44. ICML 2023Dink-Net: Neural Clustering on Large Graphs
  45. ICML 2023Directed Chain Generative Adversarial Networks
  46. ICML 2023Discrete Key-Value Bottleneck
  47. ICML 2023Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape
  48. ICML 2023Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
  49. ICML 2023Emergence of Sparse Representations from Noise
  50. ICML 2023Estimating Joint Treatment Effects by Combining Multiple Experiments

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