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 1,935 篇，第 9 / 39 页

  1. NeurIPS 2026PoEM: Predicting New RL Outcomes from Existing Policies
  2. NeurIPS 2026PortPy: A Benchmark for AI and Optimization in Cancer Radiotherapy Planning
  3. NeurIPS 2026Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
  4. NeurIPS 2026Position: Machine Learning Models for Reaction Transition States Deserve Better
  5. NeurIPS 2026Post-Selection Distributional Model Evaluation
  6. NeurIPS 2026Posterior Alternative Calibration in Ambiguous Inverse Problems
  7. NeurIPS 2026Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
  8. NeurIPS 2026Preconditioned Flow Matching
  9. NeurIPS 2026Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success
  10. NeurIPS 2026PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset
  11. NeurIPS 2026ProactBench: Beyond What The User Asked For
  12. NeurIPS 2026Probabilistic Tiny Recursive Model
  13. NeurIPS 2026probly: Uncertainty-Aware Machine Learning
  14. NeurIPS 2026ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
  15. NeurIPS 2026Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models
  16. NeurIPS 2026ProgramBench: Can Language Models Rebuild Programs From Scratch?
  17. NeurIPS 2026Progressive Signal Calibration for Medical Image Segmentation: Diagnosing and Correcting Structural Misalignment in Training Signals
  18. NeurIPS 2026Projection Learning: A Principled Way to Overcome Memorization in Distribution Learning
  19. NeurIPS 2026ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model
  20. NeurIPS 2026Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
  21. NeurIPS 2026PULSE: A Synchronized Five-Modality Dataset for Sensorimotor Coordination in Long-Horizon Daily Activities
  22. NeurIPS 2026pyCD: A Unified Benchmark for Reliable Evaluation of Cognitive Diagnosis Models
  23. NeurIPS 2026Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching
  24. NeurIPS 2026QDMouse4M: A Multi-View 3D Mouse Spontaneous Behavior Dataset with Quantum-Dot Markers
  25. NeurIPS 2026RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models
  26. NeurIPS 2026RADAR: Relative Angular Divergence Across Representations
  27. NeurIPS 2026RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis
  28. NeurIPS 2026RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
  29. NeurIPS 2026RAOP: Step-Level Resource Orchestration for LLM Agents across Edge and Cloud
  30. NeurIPS 2026Rare Disease Diagnosis Agent with Decoupled Workflows and Knowledge-Driven Self-Evaluation
  31. NeurIPS 2026Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
  32. NeurIPS 2026Real-World Dual-Pixel Raindrop Removal: A New Benchmark and Degradation-Adaptive RWKV Baseline
  33. NeurIPS 2026RealityTest: How People Probe AI Identity and Whether Models Disclose It
  34. NeurIPS 2026Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models
  35. NeurIPS 2026Recovering Clean Evaluation Metrics from Contaminated Benchmarks
  36. NeurIPS 2026Recreating Video Arenas via Automated Preference Scoring
  37. NeurIPS 2026ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition
  38. NeurIPS 2026Reflected Schrödinger Bridge Matching
  39. NeurIPS 2026Register Anything Model for Generalizable and Robust Point Cloud Registration
  40. NeurIPS 2026Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
  41. NeurIPS 2026RelFlexformer: Efficient Attention Transformers for Integrable Relative Positional Encodings
  42. NeurIPS 2026Reliable Abstention under Adversarial Injections: Lower Bounds and New Upper Bounds
  43. NeurIPS 2026Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
  44. NeurIPS 2026RepoZero: Can LLMs Generate a Code Repository from Scratch?
  45. NeurIPS 2026Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility
  46. NeurIPS 2026Representing Part-Whole Hierarchy with Nested Neuronal Coherence
  47. NeurIPS 2026RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting
  48. NeurIPS 2026Reset Dependence Is Embodied: Training Protocol Changes Which Morphologies Appear Optimal
  49. NeurIPS 2026Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
  50. NeurIPS 2026ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction

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