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 5,852 篇，第 51 / 118 页

  1. ICLR 2025HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting
  2. ICLR 2025Human Simulacra: Benchmarking the Personification of Large Language Models
  3. ICLR 2025HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
  4. ICLR 2025IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
  5. ICLR 2025IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning
  6. ICLR 2025ILLUSION: Unveiling Truth with a Comprehensive Multi-Modal, Multi-Lingual Deepfake Dataset
  7. ICLR 2025ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences
  8. ICLR 2025Imputation for prediction: beware of diminishing returns.
  9. ICLR 2025INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
  10. ICLR 2025InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
  11. ICLR 2025InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly
  12. ICLR 2025Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
  13. ICLR 2025Integrative Decoding: Improving Factuality via Implicit Self-consistency
  14. ICLR 2025Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention
  15. ICLR 2025Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
  16. ICLR 2025Inverse Constitutional AI: Compressing Preferences into Principles
  17. ICLR 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences
  18. ICLR 2025Is Large-scale Pretraining the Secret to Good Domain Generalization?
  19. ICLR 2025JPEG Inspired Deep Learning
  20. ICLR 2025JudgeBench: A Benchmark for Evaluating LLM-Based Judges
  21. ICLR 2025JudgeLM: Fine-tuned Large Language Models are Scalable Judges
  22. ICLR 2025Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
  23. ICLR 2025K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models
  24. ICLR 2025Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
  25. ICLR 2025KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks
  26. ICLR 2025LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion
  27. ICLR 2025Language Model Alignment in Multilingual Trolley Problems
  28. ICLR 2025Language Models Learn to Mislead Humans via RLHF
  29. ICLR 2025Language Representations Can be What Recommenders Need: Findings and Potentials
  30. ICLR 2025Large Language Models Often Say One Thing and Do Another
  31. ICLR 2025Law of the Weakest Link: Cross Capabilities of Large Language Models
  32. ICLR 2025Lawma: The Power of Specialization for Legal Annotation
  33. ICLR 2025Learning Color Equivariant Representations
  34. ICLR 2025Learning Continually by Spectral Regularization
  35. ICLR 2025Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
  36. ICLR 2025Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement Learning
  37. ICLR 2025LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
  38. ICLR 2025LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content
  39. ICLR 2025LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing
  40. ICLR 2025LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
  41. ICLR 2025LocoVR: Multiuser Indoor Locomotion Dataset in Virtual Reality
  42. ICLR 2025LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
  43. ICLR 2025LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning
  44. ICLR 2025Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
  45. ICLR 2025ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks
  46. ICLR 2025MANTRA: The Manifold Triangulations Assemblage
  47. ICLR 2025Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
  48. ICLR 2025Matryoshka Multimodal Models
  49. ICLR 2025McEval: Massively Multilingual Code Evaluation
  50. ICLR 2025MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation 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