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 19 / 19 页

  1. ICML 2023Rethink DARTS Search Space and Renovate a New Benchmark
  2. ICML 2023Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
  3. ICML 2023Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation
  4. ICML 2023Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
  5. ICML 2023Secure Federated Correlation Test and Entropy Estimation
  6. ICML 2023Semi-Dual Unbalanced Quadratic Optimal Transport: fast statistical rates and convergent algorithm.
  7. ICML 2023Sequential Kernelized Independence Testing
  8. ICML 2023Sequential Strategic Screening
  9. ICML 2023Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
  10. ICML 2023Short-lived High-volume Bandits
  11. ICML 2023Simple and Fast Group Robustness by Automatic Feature Reweighting
  12. ICML 2023Simple Disentanglement of Style and Content in Visual Representations
  13. ICML 2023Simplex Random Features
  14. ICML 2023Speeding Up Bellman Ford via Minimum Violation Permutations
  15. ICML 2023Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes
  16. ICML 2023Spurious Valleys and Clustering Behavior of Neural Networks
  17. ICML 2023Stable Estimation of Heterogeneous Treatment Effects
  18. ICML 2023State and parameter learning with PARIS particle Gibbs
  19. ICML 2023Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels
  20. ICML 2023Streaming Active Learning with Deep Neural Networks
  21. ICML 2023Structured Cooperative Learning with Graphical Model Priors
  22. ICML 2023Submodular Order Functions and Assortment Optimization
  23. ICML 2023Subset-Based Instance Optimality in Private Estimation
  24. ICML 2023Surrogate Module Learning: Reduce the Gradient Error Accumulation in Training Spiking Neural Networks
  25. ICML 2023TabDDPM: Modelling Tabular Data with Diffusion Models
  26. ICML 2023The Catalog Problem: Clustering and Ordering Variable-Sized Sets
  27. ICML 2023The Fast Johnson-Lindenstrauss Transform Is Even Faster
  28. ICML 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
  29. ICML 2023The Numerical Stability of Hyperbolic Representation Learning
  30. ICML 2023The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning
  31. ICML 2023Topological Point Cloud Clustering
  32. ICML 2023Towards a Persistence Diagram that is Robust to Noise and Varied Densities
  33. ICML 2023Towards Unbiased Training in Federated Open-world Semi-supervised Learning
  34. ICML 2023Towards Understanding and Reducing Graph Structural Noise for GNNs
  35. ICML 2023TRAK: Attributing Model Behavior at Scale
  36. ICML 2023Transformed Distribution Matching for Missing Value Imputation
  37. ICML 2023Two-Scale Gradient Descent Ascent Dynamics Finds Mixed Nash Equilibria of Continuous Games: A Mean-Field Perspective
  38. ICML 2023Uncertain Evidence in Probabilistic Models and Stochastic Simulators
  39. ICML 2023Unifying Nesterov's Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions
  40. ICML 2023Unlocking Slot Attention by Changing Optimal Transport Costs
  41. ICML 2023UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
  42. ICML 2023What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective
  43. ICML 2023When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
  44. ICML 2023When do Minimax-fair Learning and Empirical Risk Minimization Coincide?
  45. ICML 2023When does Privileged information Explain Away Label Noise?
  46. ICML 2023Why does Throwing Away Data Improve Worst-Group Error?
  47. ICML 2023Why Target Networks Stabilise Temporal Difference Methods
  48. ICML 2023X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion

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