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 10 / 29 页

  1. ICLR 2026PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts
  2. ICLR 2026PYRREGULAR: A Unified Framework for Irregular Time Series, with Classification Benchmarks
  3. ICLR 2026Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
  4. ICLR 2026Random Spiking Neural Networks are Stable and Spectrally Simple
  5. ICLR 2026RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
  6. ICLR 2026RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
  7. ICLR 2026Reasoning Language Model Inference Serving Unveiled: An Empirical Study
  8. ICLR 2026Reassessing Layer Pruning in LLMs: New Insights and Methods
  9. ICLR 2026RECODE: A Benchmark for Research Code DEvelopment with Interactive Human Feedback
  10. ICLR 2026Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation
  11. ICLR 2026RedacBench: Can AI Erase Your Secrets?
  12. ICLR 2026RedSage: A Cybersecurity Generalist LLM
  13. ICLR 2026Reducing Symmetry Increase in Equivariant Neural Networks
  14. ICLR 2026Referring Layer Decomposition
  15. ICLR 2026RefineBench: Evaluating Refinement Capability in Language Models
  16. ICLR 2026Reliable Evaluation of MRI Motion Correction: Dataset and Insights
  17. ICLR 2026Reliable Fine-Grained Evaluation of Natural Language Math Proofs
  18. ICLR 2026ResearchRubrics: A Benchmark of Prompts and Rubrics For Deep Research Agents
  19. ICLR 2026ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection
  20. ICLR 2026Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
  21. ICLR 2026Rethinking Continual Learning with Progressive Neural Collapse
  22. ICLR 2026Reusing Pre-Training Data at Test Time is a Compute Multiplier
  23. ICLR 2026Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
  24. ICLR 2026Revisiting the Past: Data Unlearning with Model State History
  25. ICLR 2026Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training
  26. ICLR 2026RewardEval: Advancing Reward Model Evaluation
  27. ICLR 2026Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
  28. ICLR 2026RF-MatID: Dataset and Benchmark for Radio Frequency Material Identification
  29. ICLR 2026RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
  30. ICLR 2026RIVER: Real-time Video Interaction Benchmark
  31. ICLR 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
  32. ICLR 2026RobotArena $\infty$: Unlimited Robot Benchmarking via Real-to-Sim Translation
  33. ICLR 2026Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
  34. ICLR 2026RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
  35. ICLR 2026RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers
  36. ICLR 2026Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
  37. ICLR 2026S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion
  38. ICLR 2026SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
  39. ICLR 2026Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
  40. ICLR 2026Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
  41. ICLR 2026SAIR: Enabling Deep Learning for Protein-Ligand Interactions with a Synthetic Structural Dataset
  42. ICLR 2026Same Content, Different Representations: A Controlled Study for Table QA
  43. ICLR 2026Sampling Complexity of TD and PPO in RKHS
  44. ICLR 2026SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation
  45. ICLR 2026ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
  46. ICLR 2026Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
  47. ICLR 2026Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief Generation
  48. ICLR 2026SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
  49. ICLR 2026Search Arena: Analyzing Search-Augmented LLMs
  50. ICLR 2026Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-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