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 5 / 13 页

  1. NeurIPS 2026Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
  2. NeurIPS 2026FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
  3. NeurIPS 2026FakeParts: a New Family of AI-Generated Video Forgeries
  4. NeurIPS 2026Fast and Accurate Probing of In-Training LLMs' Downstream Performances
  5. NeurIPS 2026Fast and slow gradient descent dynamics of logistic regression through weak alignment
  6. NeurIPS 2026Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers
  7. NeurIPS 2026FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model
  8. NeurIPS 2026Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
  9. NeurIPS 2026FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping
  10. NeurIPS 2026Fixed-Size Active Statistical Inference
  11. NeurIPS 2026Flash-KMeans: Fast and Memory-Efficient Exact K-Means
  12. NeurIPS 2026Flexible Intensities Matter: A comprehensive re-evaluation of Classical and Neural Temporal Point Processes
  13. NeurIPS 2026Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
  14. NeurIPS 2026Flow-Guided Target-Space Alignment via Path Consistency
  15. NeurIPS 2026FlyingDrones: A Dataset and Benchmark for Optical Flow Estimation from UAV motion
  16. NeurIPS 2026ForceBody: Force-Paired Parametric Body Motion with Torque Uncertainty
  17. NeurIPS 2026Fourier Contour Learning for Efficient and Traceable Cardiac MRI Quantification
  18. NeurIPS 2026FrameSelect: A Unified Library for Video Frame Selection and Evaluation
  19. NeurIPS 2026Frontier Task Synthesis Via Solution-Centric Evolution
  20. NeurIPS 2026fxBench: Evaluating and Understanding Formula Suggestions in Spreadsheets
  21. NeurIPS 2026Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
  22. NeurIPS 2026GEMS-3D: A Large-Scale 3D Gravity, Electrical, Magnetic, and Seismic Earth Simulation Dataset for Multimodal Geophysical Learning
  23. NeurIPS 2026GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
  24. NeurIPS 2026Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
  25. NeurIPS 2026GeoDial: A Multimodal Dialog Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns
  26. NeurIPS 2026Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension
  27. NeurIPS 2026Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images
  28. NeurIPS 2026gfnx: Fast and Scalable Library for Generative Flow Networks in JAX
  29. NeurIPS 2026GMOS: Grounding Moving Object Segmentation in 3D Space and Time
  30. NeurIPS 2026GPT-Image-Edit-1M: An Auditable Million-Scale Dataset for Instruction-Guided Image Editing
  31. NeurIPS 2026GUI-Libra: Data-Efficient Post-Training for Reliable Reasoning-and-Acting in Native GUI Agents
  32. NeurIPS 2026Gumbo: Gumbel Optimized High-Temperature Speculative Sampling
  33. NeurIPS 2026Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
  34. NeurIPS 2026haphazard: A unified library and benchmark for online learning under varying feature availability
  35. NeurIPS 2026Harbor Adapters and Harbor-Mix: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
  36. NeurIPS 2026Harnessing Accurate and Automatic Trend Detection in Data Streams via Tbps-Level Inference
  37. NeurIPS 2026Harnessing Data Asymmetry in Manifold Learning
  38. NeurIPS 2026Heavy-Tailed Flow Matching via Random Clocks
  39. NeurIPS 2026HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
  40. NeurIPS 2026Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking
  41. NeurIPS 2026Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality
  42. NeurIPS 2026Hierarchical Agglomerative Clustering via Relaxed Representatives
  43. NeurIPS 2026Hierarchical Graph Representation Learning with Pooling-Induced Substructures
  44. NeurIPS 2026High Performance Differentially Private Fine-Tuning using Dataset Distillation
  45. NeurIPS 2026High-Dimensional Conditional Independence Testing via Random Projection Aggregation
  46. NeurIPS 2026HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
  47. NeurIPS 2026Hint Tuning: Less Data Makes Better Reasoners
  48. NeurIPS 2026HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations
  49. NeurIPS 2026How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
  50. NeurIPS 2026How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models

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