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 623 篇，第 8 / 13 页

  1. NeurIPS 2026NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
  2. NeurIPS 2026NNCoxKL: Risk-Set Distillation from Probability-Free Prognostic Teachers for Deep Cox Models
  3. NeurIPS 2026nnTrace: Detecting and Localizing Silent Bugs in Distributed Training
  4. NeurIPS 2026Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
  5. NeurIPS 2026Non-Linear Pricing Restores Tractability for a Data Seller
  6. NeurIPS 2026Norm Anchors Make Model Edits Last
  7. NeurIPS 2026nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving
  8. NeurIPS 2026Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty
  9. NeurIPS 2026OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
  10. NeurIPS 2026ODDR: One-Step Deshadow Diffusion via Reward Guidance
  11. NeurIPS 2026OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
  12. NeurIPS 2026Offline Preference-Based Trajectory Evaluation
  13. NeurIPS 2026Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
  14. NeurIPS 2026OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning
  15. NeurIPS 2026On Differential Private $\ell_1$, $\ell_2$ and $\ell_p^p$ Distance Queries
  16. NeurIPS 2026On Nash Equilibria in Participatory Budgeting with Donations and Beyond
  17. NeurIPS 2026On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference
  18. NeurIPS 2026On the Convergence of Multicalibration Gradient Boosting
  19. NeurIPS 2026On the Existence of Uniformly Optimal Policies in MDPs under Epistemic Uncertainty
  20. NeurIPS 2026On the Geometry and Latent-Space Composition of Hypernetwork-Generated LoRAs
  21. NeurIPS 2026One Temperature to Rule Them All?
  22. NeurIPS 2026Online Maximization of Non-Decomposable Test and Population Utilities
  23. NeurIPS 2026OpenSanctions Pairs: A Large-Scale Dataset for Pairwise Entity Matching
  24. NeurIPS 2026OpenView: Empowering MLLMs with Out-of-view VQA
  25. NeurIPS 2026OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation
  26. NeurIPS 2026OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
  27. NeurIPS 2026Optimal In-context Adaptivity and Distributional Robustness of Transformers
  28. NeurIPS 2026Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
  29. NeurIPS 2026Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
  30. NeurIPS 2026OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
  31. NeurIPS 2026Panoptic Saliency Ranking
  32. NeurIPS 2026PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World
  33. NeurIPS 2026PaperLens: How Predictable Is Paper Acceptance?
  34. NeurIPS 2026Participatory ML for Social Harm Should be Constructed, Validated and Reasoned Through First-Person Accounts
  35. NeurIPS 2026PatchBench: Measuring Collateral Damage in Activation Patching
  36. NeurIPS 2026Patching Up Circuit Learning on Images
  37. NeurIPS 2026PatchKV: Weight Space Compensation of KV Cache
  38. NeurIPS 2026PatchScout: Thematic Web Data Collection via Information Foraging
  39. NeurIPS 2026Path-Guided Flow Matching for Dataset Distillation
  40. NeurIPS 2026PE-SHAP: Causally Interpretable Path-Wise Shapley Explanations
  41. NeurIPS 2026PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction
  42. NeurIPS 2026Per-Starting-Point Plausibility and Diversity Bounds for Score-Based Diffusion Models
  43. NeurIPS 2026Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  44. NeurIPS 2026Personal Visual Memory from Explicit and Implicit Evidence
  45. NeurIPS 2026PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos
  46. NeurIPS 2026PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos
  47. NeurIPS 2026PhysTC: A Physics-Enhanced Dataset and Architecture for High-Precision Tropical Cyclone Forecasting
  48. NeurIPS 2026PhyTS: A Benchmark for Scientific Time Series
  49. NeurIPS 2026PINNBench: A Benchmark and Evaluation Study of Training Policy Selection in Hybrid PINN-Operator Solvers
  50. NeurIPS 2026PINNeval: A Comprehensive Evaluation Standard for Physics-Informed Neural Networks

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