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 1,987 篇，第 40 / 40 页

  1. NeurIPS 2026TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates
  2. NeurIPS 2026TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
  3. NeurIPS 2026Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
  4. NeurIPS 2026Uncertainty Quantification for Large Language Diffusion Models
  5. NeurIPS 2026Understanding the Interplay between Memorization and Learning in Large Language Models
  6. NeurIPS 2026UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
  7. NeurIPS 2026Unlearning Diffusion Policies via Relative Fisher Forgetting
  8. NeurIPS 2026VAANI: Capturing the language landscape for an inclusive digital India
  9. NeurIPS 2026Vendi Anomaly Scores for Efficient and Accurate Anomaly Detection
  10. NeurIPS 2026VeriVul: A Verification-Guided Framework for Generating Realistic Vulnerability Benchmarks
  11. NeurIPS 2026ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins
  12. NeurIPS 2026Visual Robustness and Neural Alignment in a Shared Foraging Task: The Mouse vs. AI Benchmark
  13. NeurIPS 2026Vortex: Efficient and Programmable Sparse Attention Serving
  14. NeurIPS 2026VTBench: Disentangled and Human-Aligned Evaluation for Image-Based Virtual Try-on
  15. NeurIPS 2026We Need to Improve Benchmarks in AI for Mathematics
  16. NeurIPS 2026WebSpatial: A Benchmarking Framework of Spatial Intelligence via Web-based Runtime Environments
  17. NeurIPS 2026Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors
  18. NeurIPS 2026Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
  19. NeurIPS 2026What Cohort INRs Encode, and Where to Freeze Them
  20. NeurIPS 2026What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
  21. NeurIPS 2026What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation
  22. NeurIPS 2026What Transformer FFNs Never See: Theory, Diagnosis, and Lightweight Remediation
  23. NeurIPS 2026When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
  24. NeurIPS 2026When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
  25. NeurIPS 2026When Do Learned State Representations Break Sensitivity Analysis?
  26. NeurIPS 2026When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
  27. NeurIPS 2026When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks
  28. NeurIPS 2026Where Tabular Foundation Models Falter on Genetic Data: Datasets That Expose and Provide a Path to Address the Gap
  29. NeurIPS 2026Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
  30. NeurIPS 2026Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video LLMs
  31. NeurIPS 2026Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
  32. NeurIPS 2026Why Heavy-Tailed Weights Predict Model Quality
  33. NeurIPS 2026WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife
  34. NeurIPS 2026Winfree Oscillatory Neural Network
  35. NeurIPS 2026Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
  36. NeurIPS 2026X-Palm: Paired Multispectral-to-Smartphone Dataset for Cross-Domain Palmprint Authentication
  37. NeurIPS 2026XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity

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