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 419 篇，第 5 / 9 页

  1. ICLR 2025KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks
  2. ICLR 2025LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion
  3. ICLR 2025Language Model Alignment in Multilingual Trolley Problems
  4. ICLR 2025Language Models Learn to Mislead Humans via RLHF
  5. ICLR 2025Language Representations Can be What Recommenders Need: Findings and Potentials
  6. ICLR 2025Large Language Models Often Say One Thing and Do Another
  7. ICLR 2025Law of the Weakest Link: Cross Capabilities of Large Language Models
  8. ICLR 2025Lawma: The Power of Specialization for Legal Annotation
  9. ICLR 2025Learning Color Equivariant Representations
  10. ICLR 2025Learning Continually by Spectral Regularization
  11. ICLR 2025Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
  12. ICLR 2025Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement Learning
  13. ICLR 2025LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
  14. ICLR 2025LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content
  15. ICLR 2025LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing
  16. ICLR 2025LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
  17. ICLR 2025LocoVR: Multiuser Indoor Locomotion Dataset in Virtual Reality
  18. ICLR 2025LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
  19. ICLR 2025LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning
  20. ICLR 2025Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
  21. ICLR 2025ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks
  22. ICLR 2025MANTRA: The Manifold Triangulations Assemblage
  23. ICLR 2025Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
  24. ICLR 2025Matryoshka Multimodal Models
  25. ICLR 2025McEval: Massively Multilingual Code Evaluation
  26. ICLR 2025MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models
  27. ICLR 2025Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets
  28. ICLR 2025MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
  29. ICLR 2025MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
  30. ICLR 2025metabench - A Sparse Benchmark of Reasoning and Knowledge in Large Language Models
  31. ICLR 2025MetaOOD: Automatic Selection of OOD Detection Models
  32. ICLR 2025MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
  33. ICLR 2025MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
  34. ICLR 2025miniCTX: Neural Theorem Proving with (Long-)Contexts
  35. ICLR 2025Mitigating Memorization in Language Models
  36. ICLR 2025MixEval-X: Any-to-any Evaluations from Real-world Data Mixture
  37. ICLR 2025Mixture of In-Context Prompters for Tabular PFNs
  38. ICLR 2025MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
  39. ICLR 2025MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection
  40. ICLR 2025MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark
  41. ICLR 2025MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  42. ICLR 2025MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
  43. ICLR 2025MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
  44. ICLR 2025MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
  45. ICLR 2025MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions
  46. ICLR 2025MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation
  47. ICLR 2025MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents
  48. ICLR 2025MMTEB: Massive Multilingual Text Embedding Benchmark
  49. ICLR 2025MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
  50. ICLR 2025MotherNet: Fast Training and Inference via Hyper-Network Transformers

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