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 7 / 13 页

  1. NeurIPS 2026LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation
  2. NeurIPS 2026LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure
  3. NeurIPS 2026LLMs can construct powerful representations and streamline sample-efficient supervised learning
  4. NeurIPS 2026Log-Likelihood, Simpson’s Paradox, and the Detection of Machine-Generated Text
  5. NeurIPS 2026Logical Distillation of Transformer Encoders
  6. NeurIPS 2026Looped Diffusion Language Models
  7. NeurIPS 2026LoopNav: Benchmarking Spatial Consistency in World Models
  8. NeurIPS 2026Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
  9. NeurIPS 2026LSC-Parlament: An Automatically Aligned Catalan Sign Language Dataset from Parliament Videos.
  10. NeurIPS 2026Magnitude-preserving Layers Enable Efficient GANs
  11. NeurIPS 2026Marginal-Nonuniform Multiclass Learning
  12. NeurIPS 2026Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking
  13. NeurIPS 2026Masked Generative Pretraining Improves Cross-Dataset Transfer in Pixel-Space Diffusion
  14. NeurIPS 2026Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment
  15. NeurIPS 2026Matrix-Free Natural Gradient via Stochastic Truncated Metrics
  16. NeurIPS 2026MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning
  17. NeurIPS 2026Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
  18. NeurIPS 2026Measuring Coherence in Predictive Models
  19. NeurIPS 2026Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
  20. NeurIPS 2026MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
  21. NeurIPS 2026MEME: Multi-Entity & Evolving Memory Evaluation
  22. NeurIPS 2026Mesh-Free Convolution: Learned Spectral Attenuation and Transport
  23. NeurIPS 2026Metropolis-Adjusted Diffusion Models
  24. NeurIPS 2026Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling
  25. NeurIPS 2026MEV: A Multi-Event Video Dataset for Long-Take Generation
  26. NeurIPS 2026Mind the Gap: Dataset and Fine-grained Evaluation for Inline Audio Descriptions
  27. NeurIPS 2026Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
  28. NeurIPS 2026MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception
  29. NeurIPS 2026MLLMs Fail to Refuse when Using Tools Agentically
  30. NeurIPS 2026MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs
  31. NeurIPS 2026Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds
  32. NeurIPS 2026Model Distribution-Aware Multimodal Dataset Distillation
  33. NeurIPS 2026Model-based Bootstrap of Controlled Markov Chains
  34. NeurIPS 2026ModelLens: Finding the Best for Your Task from Myriads of Models
  35. NeurIPS 2026Monoculture Robust Learning
  36. NeurIPS 2026MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
  37. NeurIPS 2026Monroe: A Molecular Foundation Model for In-context Probabilistic Inference
  38. NeurIPS 2026MoSE3: Learning World-Space SE(3) at Every Pixel
  39. NeurIPS 2026MSAlign: Aligning Molecular and Mass Spectra Foundation Models for Metabolite Identification
  40. NeurIPS 2026MSConsensus: A Hundred-Million-Scale, Batch-Effect–Suppressed Dataset and Benchmark for Proteomics Machine Learning
  41. NeurIPS 2026Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-Site Wearables
  42. NeurIPS 2026Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism
  43. NeurIPS 2026NanoFold: Designing Reproducible Protein Structure Benchmarks through Principled Sampling
  44. NeurIPS 2026Nautilus: From One Prompt to Plug-and-Play Robot Learning
  45. NeurIPS 2026Near-Optimal Stochastic Linear Bandits with Delay
  46. NeurIPS 2026NEST: Nascent Encoded Steganographic Thoughts
  47. NeurIPS 2026NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Model
  48. NeurIPS 2026Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP
  49. NeurIPS 2026Neural Optimal Transport in Hilbert Spaces
  50. NeurIPS 2026New Coresets for Fair Clustering

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