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 1,432 篇，第 15 / 29 页

  1. ICLR 2025Century: A Framework and Dataset for Evaluating Historical Contextualisation of Sensitive Images
  2. ICLR 2025CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness
  3. ICLR 2025CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
  4. ICLR 2025ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
  5. ICLR 2025Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
  6. ICLR 2025ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains
  7. ICLR 2025CipherPrune: Efficient and Scalable Private Transformer Inference
  8. ICLR 2025CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models
  9. ICLR 2025ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models
  10. ICLR 2025CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark
  11. ICLR 2025Commit0: Library Generation from Scratch
  12. ICLR 2025Confidence Elicitation: A New Attack Vector for Large Language Models
  13. ICLR 2025Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback
  14. ICLR 2025Consistency Checks for Language Model Forecasters
  15. ICLR 2025Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets
  16. ICLR 2025ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments
  17. ICLR 2025Coreset Selection via Reducible Loss in Continual Learning
  18. ICLR 2025Coreset Spectral Clustering
  19. ICLR 2025Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
  20. ICLR 2025Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits
  21. ICLR 2025cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM
  22. ICLR 2025CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
  23. ICLR 2025Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
  24. ICLR 2025CycleResearcher: Improving Automated Research via Automated Review
  25. ICLR 2025DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
  26. ICLR 2025Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning
  27. ICLR 2025Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks
  28. ICLR 2025Dataset Ownership Verification in Contrastive Pre-trained Models
  29. ICLR 2025Difference-of-submodular Bregman Divergence
  30. ICLR 2025Differentiable Integer Linear Programming
  31. ICLR 2025Diffusing States and Matching Scores: A New Framework for Imitation Learning
  32. ICLR 2025Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
  33. ICLR 2025Diffusion Models as Cartoonists: The Curious Case of High Density Regions
  34. ICLR 2025DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
  35. ICLR 2025Distilling Dataset into Neural Field
  36. ICLR 2025Do Large Language Models Truly Understand Geometric Structures?
  37. ICLR 2025Do LLMs estimate uncertainty well in instruction-following?
  38. ICLR 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
  39. ICLR 2025Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives
  40. ICLR 2025Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
  41. ICLR 2025DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
  42. ICLR 2025DRoP: Distributionally Robust Data Pruning
  43. ICLR 2025Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment
  44. ICLR 2025Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
  45. ICLR 2025Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
  46. ICLR 2025Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
  47. ICLR 2025ECD: A Machine Learning Benchmark for Predicting Enhanced-Precision Electronic Charge Density in Crystalline Inorganic Materials
  48. ICLR 2025Efficient Cross-Episode Meta-RL
  49. ICLR 2025ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
  50. ICLR 2025EmbedLLM: Learning Compact Representations of Large Language 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