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 16 / 19 页

  1. ICML 2024The Fundamental Limits of Least-Privilege Learning
  2. ICML 2024The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
  3. ICML 2024Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability
  4. ICML 2024Tilt and Average : Geometric Adjustment of the Last Layer for Recalibration
  5. ICML 2024Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers
  6. ICML 2024tinyBenchmarks: evaluating LLMs with fewer examples
  7. ICML 2024Total Variation Distance Meets Probabilistic Inference
  8. ICML 2024Towards Causal Foundation Model: on Duality between Optimal Balancing and Attention
  9. ICML 2024Towards Compositionality in Concept Learning
  10. ICML 2024Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations
  11. ICML 2024Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
  12. ICML 2024Towards Modular LLMs by Building and Reusing a Library of LoRAs
  13. ICML 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
  14. ICML 2024Towards Scalable and Versatile Weight Space Learning
  15. ICML 2024Trained Random Forests Completely Reveal your Dataset
  16. ICML 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
  17. ICML 2024Transitional Uncertainty with Layered Intermediate Predictions
  18. ICML 2024Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning
  19. ICML 2024Trustless Audits without Revealing Data or Models
  20. ICML 2024Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
  21. ICML 2024Two-Stage Shadow Inclusion Estimation: An IV Approach for Causal Inference under Latent Confounding and Collider Bias
  22. ICML 2024ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback
  23. ICML 2024Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations
  24. ICML 2024Unveiling Privacy, Memorization, and Input Curvature Links
  25. ICML 2024VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
  26. ICML 2024Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformer
  27. ICML 2024Weighted distance nearest neighbor condensing
  28. ICML 2024What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
  29. ICML 2024What is Dataset Distillation Learning?
  30. ICML 2024What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks
  31. ICML 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?
  32. ICML 2024Winner-takes-all learners are geometry-aware conditional density estimators
  33. ICML 2023A Flexible Diffusion Model
  34. ICML 2023A Generalization of ViT/MLP-Mixer to Graphs
  35. ICML 2023A New PHO-rmula for Improved Performance of Semi-Structured Networks
  36. ICML 2023A Picture of the Space of Typical Learnable Tasks
  37. ICML 2023A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
  38. ICML 2023A Study on Transformer Configuration and Training Objective
  39. ICML 2023Achieving Linear Speedup in Non-IID Federated Bilevel Learning
  40. ICML 2023Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
  41. ICML 2023An Effective Meaningful Way to Evaluate Survival Models
  42. ICML 2023Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation
  43. ICML 2023Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
  44. ICML 2023Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.
  45. ICML 2023Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?
  46. ICML 2023Atari-5: Distilling the Arcade Learning Environment down to Five Games
  47. ICML 2023Automatic Data Augmentation via Invariance-Constrained Learning
  48. ICML 2023Auxiliary Learning as an Asymmetric Bargaining Game
  49. ICML 2023Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
  50. ICML 2023Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies

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