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 623 篇，第 4 / 13 页

  1. NeurIPS 2026Distribution Corrected Decision Transformer for Offline Reinforcement Learning with Imbalanced Datasets
  2. NeurIPS 2026Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
  3. NeurIPS 2026Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
  4. NeurIPS 2026Do LLMs Feel Social Pressure? Locating and Steering Social Desirability Bias in LLMs
  5. NeurIPS 2026Do You CARE to Generalize? Extracting Robust Concept Directions from LLMs
  6. NeurIPS 2026DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
  7. NeurIPS 2026Domain-Conditioned Class Imbalance: Why Global Class Balance Fails Across Domains
  8. NeurIPS 2026Doomed to Re-Annotate, Forever: The ImageNet Story
  9. NeurIPS 2026DopplerWild: A Doppler Dataset and Benchmark for Human Kinematic Understanding in the Wild
  10. NeurIPS 2026Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
  11. NeurIPS 2026Dual Dimensionality for Local and Global Attention
  12. NeurIPS 2026Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
  13. NeurIPS 2026DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?
  14. NeurIPS 2026DynaCell: an Evaluation Framework for Dynamic 3D Virtual Staining of Live Cells
  15. NeurIPS 2026Dynamic k-center clustering with lifetimes
  16. NeurIPS 2026Dynamic Model Merging Made Slim
  17. NeurIPS 2026Dynamic Treatment on Networks
  18. NeurIPS 2026ECG Dataset with Multi-Expert Annotations and Delineations
  19. NeurIPS 2026EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function
  20. NeurIPS 2026ECLIPSE: A Spacecraft Rendezvous Trajectories Dataset with Controlled In-Orbit Lighting Conditions
  21. NeurIPS 2026EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation
  22. NeurIPS 2026EDMA: Entropy-Driven Multimodal Answering
  23. NeurIPS 2026Efficient Benchmarking Is Just Feature Selection and Multiple Regression
  24. NeurIPS 2026Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
  25. NeurIPS 2026Efficient evaluation and error pattern discovery for blackbox AI systems
  26. NeurIPS 2026Efficient Evaluation of LLM Performance with Statistical Guarantees
  27. NeurIPS 2026Efficient Retrosynthesis Prediction with Integral Flow Matching and Latent Inversion
  28. NeurIPS 2026EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
  29. NeurIPS 2026EgoSurgHands: An Egocentric 3D Hand Pose Dataset & Benchmark for Open-Surgery Training
  30. NeurIPS 2026Emergent Misalignment as Data-Mediated Transfer
  31. NeurIPS 2026EpistasisBench: Revealing Structural Limitations of Zero-Shot Protein Language Models
  32. NeurIPS 2026Epistemic Pairwise Maximin Share
  33. NeurIPS 2026Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning
  34. NeurIPS 2026Estimating Model-Level Membership Inference Vulnerability Without Reference Models
  35. NeurIPS 2026EvalAwareBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
  36. NeurIPS 2026Evaluating Compositional Generalization in Transformers: The Role of Composition Equivalence and Module Coverage
  37. NeurIPS 2026Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning
  38. NeurIPS 2026Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
  39. NeurIPS 2026EVALUATION CARDS: An Interpretive Layer for AI Evaluation Reporting
  40. NeurIPS 2026Explanation Multiplicity in SHAP: Characterization and Assessment
  41. NeurIPS 2026Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring Starts
  42. NeurIPS 2026Exposing and Mitigating Temporal Attack in Deepfake Video Detection
  43. NeurIPS 2026Extending Myerson's Optimal Auctions to Correlated Bidders via Neural Network Interpolation
  44. NeurIPS 2026ExtrapAir: Air Quality Inference at Unmonitored Locations via Weather-Bridged Spatial Attention
  45. NeurIPS 2026Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
  46. NeurIPS 2026FacePhys: State of the Heart Learning
  47. NeurIPS 2026Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
  48. NeurIPS 2026Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes
  49. NeurIPS 2026Fair Range k-Supplier Clustering in Offline and Streaming Models
  50. NeurIPS 2026Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs

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