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 17 / 29 页

  1. ICLR 2025HELMET: How to Evaluate Long-context Models Effectively and Thoroughly
  2. ICLR 2025HelpSteer2-Preference: Complementing Ratings with Preferences
  3. ICLR 2025Herald: A Natural Language Annotated Lean 4 Dataset
  4. ICLR 2025HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts
  5. ICLR 2025How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension
  6. ICLR 2025How efficient is LLM-generated code? A rigorous & high-standard benchmark
  7. ICLR 2025How Far Are We from True Unlearnability?
  8. ICLR 2025How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
  9. ICLR 2025How new data permeates LLM knowledge and how to dilute it
  10. ICLR 2025How to Evaluate Reward Models for RLHF
  11. ICLR 2025HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
  12. ICLR 2025HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting
  13. ICLR 2025Human Simulacra: Benchmarking the Personification of Large Language Models
  14. ICLR 2025HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
  15. ICLR 2025IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
  16. ICLR 2025IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning
  17. ICLR 2025ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake Dataset
  18. ICLR 2025ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences
  19. ICLR 2025Imputation for prediction: beware of diminishing returns.
  20. ICLR 2025INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
  21. ICLR 2025InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
  22. ICLR 2025InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly
  23. ICLR 2025Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
  24. ICLR 2025Integrative Decoding: Improving Factuality via Implicit Self-consistency
  25. ICLR 2025Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention
  26. ICLR 2025Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
  27. ICLR 2025Inverse Constitutional AI: Compressing Preferences into Principles
  28. ICLR 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences
  29. ICLR 2025Is Large-scale Pretraining the Secret to Good Domain Generalization?
  30. ICLR 2025JPEG Inspired Deep Learning
  31. ICLR 2025JudgeBench: A Benchmark for Evaluating LLM-Based Judges
  32. ICLR 2025JudgeLM: Fine-tuned Large Language Models are Scalable Judges
  33. ICLR 2025Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
  34. ICLR 2025K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models
  35. ICLR 2025Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
  36. ICLR 2025KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks
  37. ICLR 2025LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion
  38. ICLR 2025Language Model Alignment in Multilingual Trolley Problems
  39. ICLR 2025Language Models Learn to Mislead Humans via RLHF
  40. ICLR 2025Language Representations Can be What Recommenders Need: Findings and Potentials
  41. ICLR 2025Large Language Models Often Say One Thing and Do Another
  42. ICLR 2025Law of the Weakest Link: Cross Capabilities of Large Language Models
  43. ICLR 2025Lawma: The Power of Specialization for Legal Annotation
  44. ICLR 2025Learning Color Equivariant Representations
  45. ICLR 2025Learning Continually by Spectral Regularization
  46. ICLR 2025Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
  47. ICLR 2025Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement Learning
  48. ICLR 2025LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
  49. ICLR 2025LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content
  50. ICLR 2025LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

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