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 24 / 39 页

  1. NeurIPS 2025SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models
  2. NeurIPS 2025Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
  3. NeurIPS 2025SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
  4. NeurIPS 2025SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
  5. NeurIPS 2025SWE-bench Goes Live!
  6. NeurIPS 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
  7. NeurIPS 2025SWE-smith: Scaling Data for Software Engineering Agents
  8. NeurIPS 2025SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
  9. NeurIPS 2025Synergistic Tensor and Pipeline Parallelism
  10. NeurIPS 2025T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning
  11. NeurIPS 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
  12. NeurIPS 2025TabArena: A Living Benchmark for Machine Learning on Tabular Data
  13. NeurIPS 2025TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models
  14. NeurIPS 2025TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation
  15. NeurIPS 2025TAPAS: Datasets for Learning the Learning with Errors Problem
  16. NeurIPS 2025Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models
  17. NeurIPS 2025TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video
  18. NeurIPS 2025TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
  19. NeurIPS 2025Tensor Decomposition Networks for Accelerating Machine Learning Force Field Computations
  20. NeurIPS 2025Tensor Product Attention Is All You Need
  21. NeurIPS 2025Tensor-Parallelism with Partially Synchronized Activations
  22. NeurIPS 2025The Best Instruction-Tuning Data are Those That Fit
  23. NeurIPS 2025The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
  24. NeurIPS 2025The emergence of sparse attention: impact of data distribution and benefits of repetition
  25. NeurIPS 2025The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
  26. NeurIPS 2025The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
  27. NeurIPS 2025The Impact of Coreset Selection on Spurious Correlations and Group Robustness
  28. NeurIPS 2025The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
  29. NeurIPS 2025The Rashomon Set Has It All: Analyzing Trustworthiness of Trees under Multiplicity
  30. NeurIPS 2025The Temporal Graph of Bitcoin Transactions
  31. NeurIPS 2025TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
  32. NeurIPS 2025ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation
  33. NeurIPS 2025ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
  34. NeurIPS 2025This Time is Different: An Observability Perspective on Time Series Foundation Models
  35. NeurIPS 2025Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations
  36. NeurIPS 2025Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced Distortions
  37. NeurIPS 2025THUNDER: Tile-level Histopathology image UNDERstanding benchmark
  38. NeurIPS 2025TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising
  39. NeurIPS 2025Tight Lower Bounds and Improved Convergence in Performative Prediction
  40. NeurIPS 2025Tightening Regret Lower and Upper Bounds in Restless Rising Bandits
  41. NeurIPS 2025Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
  42. NeurIPS 2025Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
  43. NeurIPS 2025TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
  44. NeurIPS 2025Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
  45. NeurIPS 2025Torch-Uncertainty: Deep Learning Uncertainty Quantification
  46. NeurIPS 2025Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation
  47. NeurIPS 2025Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
  48. NeurIPS 2025Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis
  49. NeurIPS 2025Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
  50. NeurIPS 2025Towards Automated Petrography

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