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 937 篇，第 11 / 19 页

  1. ICLR 2023Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
  2. ICLR 2023Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation
  3. ICLR 2023Rethinking Symbolic Regression: Morphology and Adaptability in the Context of Evolutionary Algorithms
  4. ICLR 2023Reversible Column Networks
  5. ICLR 2023Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective
  6. ICLR 2023S-NeRF: Neural Radiance Fields for Street Views
  7. ICLR 2023Scenario-based Question Answering with Interacting Contextual Properties
  8. ICLR 2023Score-based Continuous-time Discrete Diffusion Models
  9. ICLR 2023Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
  10. ICLR 2023Sign and Basis Invariant Networks for Spectral Graph Representation Learning
  11. ICLR 2023Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
  12. ICLR 2023SMART: Sentences as Basic Units for Text Evaluation
  13. ICLR 2023Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
  14. ICLR 2023Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
  15. ICLR 2023Spherical Sliced-Wasserstein
  16. ICLR 2023Spikformer: When Spiking Neural Network Meets Transformer
  17. ICLR 2023Supervision Complexity and its Role in Knowledge Distillation
  18. ICLR 2023Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow
  19. ICLR 2023The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation
  20. ICLR 2023The Curious Case of Benign Memorization
  21. ICLR 2023The Dark Side of AutoML: Towards Architectural Backdoor Search
  22. ICLR 2023The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
  23. ICLR 2023Toward Adversarial Training on Contextualized Language Representation
  24. ICLR 2023Towards Better Selective Classification
  25. ICLR 2023Towards Inferential Reproducibility of Machine Learning Research
  26. ICLR 2023Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
  27. ICLR 2023Transferable Unlearnable Examples
  28. ICLR 2023TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning
  29. ICLR 2023TypeT5: Seq2seq Type Inference using Static Analysis
  30. ICLR 2023Unbiased Supervised Contrastive Learning
  31. ICLR 2023Understanding Influence Functions and Datamodels via Harmonic Analysis
  32. ICLR 2023Understanding new tasks through the lens of training data via exponential tilting
  33. ICLR 2023UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks
  34. ICLR 2023UniMax: Fairer and More Effective Language Sampling for Large-Scale Multilingual Pretraining
  35. ICLR 2023Unsupervised visualization of image datasets using contrastive learning
  36. ICLR 2023Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
  37. ICLR 2023What Can we Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers?
  38. ICLR 2023What Is Missing in IRM Training and Evaluation? Challenges and Solutions
  39. ICLR 2023What learning algorithm is in-context learning? Investigations with linear models
  40. ICLR 2023When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?
  41. ICLR 2023When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
  42. ICLR 2023When to Make and Break Commitments?
  43. ICLR 2023Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions
  44. ICLR 2023WikiWhy: Answering and Explaining Cause-and-Effect Questions
  45. ICML 2023A Flexible Diffusion Model
  46. ICML 2023A Generalization of ViT/MLP-Mixer to Graphs
  47. ICML 2023A New PHO-rmula for Improved Performance of Semi-Structured Networks
  48. ICML 2023A Picture of the Space of Typical Learnable Tasks
  49. ICML 2023A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
  50. ICML 2023A Study on Transformer Configuration and Training Objective

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