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 19 / 39 页

  1. NeurIPS 2025IRRISIGHT: A Large-Scale Multimodal Dataset and Scalable Pipeline to Address Irrigation and Water Management in Agriculture
  2. NeurIPS 2025Is Artificial Intelligence Generated Image Detection a Solved Problem?
  3. NeurIPS 2025Is This Tracker On? A Benchmark Protocol for Dynamic Tracking
  4. NeurIPS 2025Isotropic Noise in Stochastic and Quantum Convex Optimization
  5. NeurIPS 2025Jacobian-Based Interpretation of Nonlinear Neural Encoding Model
  6. NeurIPS 2025Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models
  7. NeurIPS 2025KAIROS: Scalable Model-Agnostic Data Valuation
  8. NeurIPS 2025KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
  9. NeurIPS 2025KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge
  10. NeurIPS 2025Kuramoto Orientation Diffusion Models
  11. NeurIPS 2025LabelAny3D: Label Any Object 3D in the Wild
  12. NeurIPS 2025Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale
  13. NeurIPS 2025Language Models (Mostly) Know When to Stop Reading
  14. NeurIPS 2025LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts
  15. NeurIPS 2025LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought
  16. NeurIPS 2025Leader360V: A Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment
  17. NeurIPS 2025Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online Data
  18. NeurIPS 2025Learning Parameterized Skills from Demonstrations
  19. NeurIPS 2025Learning single index models via harmonic decomposition
  20. NeurIPS 2025Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks
  21. NeurIPS 2025Learning to Solve Complex Problems via Dataset Decomposition
  22. NeurIPS 2025LexiCon: a Benchmark for Planning under Temporal Constraints in Natural Language
  23. NeurIPS 2025LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
  24. NeurIPS 2025LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
  25. NeurIPS 2025Linguini: A benchmark for language-agnostic linguistic reasoning
  26. NeurIPS 2025LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery
  27. NeurIPS 2025Listening to the Brain: Multi-Band sEEG Auditory Reconstruction via Dynamic Spatio-Temporal Hypergraphs
  28. NeurIPS 2025LithoSim: A Large, Holistic Lithography Simulation Benchmark for AI-Driven Semiconductor Manufacturing
  29. NeurIPS 2025Long-term Intracortical Neural activity and Kinematics (LINK): An intracortical neural dataset for chronic brain-machine interfaces, neuroscience, and machine learning
  30. NeurIPS 2025LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
  31. NeurIPS 2025LTD-Bench: Evaluating Large Language Models by Letting Them Draw
  32. NeurIPS 2025Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks
  33. NeurIPS 2025MARS-VFL: A Unified Benchmark for Vertical Federated Learning with Realistic Evaluation
  34. NeurIPS 2025Massive Sound Embedding Benchmark (MSEB)
  35. NeurIPS 2025Matchings Under Biased and Correlated Evaluations
  36. NeurIPS 2025MathArena: Evaluating LLMs on Uncontaminated Math Competitions
  37. NeurIPS 2025Measuring AI Ability to Complete Long Software Tasks
  38. NeurIPS 2025Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training
  39. NeurIPS 2025Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
  40. NeurIPS 2025Measuring what Matters: Construct Validity in Large Language Model Benchmarks
  41. NeurIPS 2025MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks
  42. NeurIPS 2025MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
  43. NeurIPS 2025MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives
  44. NeurIPS 2025MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
  45. NeurIPS 2025MedSG-Bench: A Benchmark for Medical Image Sequences Grounding
  46. NeurIPS 2025MergeBench: A Benchmark for Merging Domain-Specialized LLMs
  47. NeurIPS 2025MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
  48. NeurIPS 2025Merlin L48 Spectrogram Dataset
  49. NeurIPS 2025Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex
  50. NeurIPS 2025Metritocracy: Representative Metrics for Lite Benchmarks

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