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 24 / 118 页

  1. ICML 2026Decoupling The "What" and "Where" With Polar Coordinate Positional Embedding
  2. ICML 2026Deep Trajectory Supervision: Deep Supervision Strikes Back
  3. ICML 2026Delegation and Verification under AI
  4. ICML 2026Detecting Errors in AI-Generated Annotations: When and Why Semantic Neighbors Help
  5. ICML 2026Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?
  6. ICML 2026Dimensionality Reduction with Point-distributions Similarity Invariant
  7. ICML 2026DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
  8. ICML 2026Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
  9. ICML 2026Divide and Contrast: Learning Robust Temporal Features without Augmentation
  10. ICML 2026DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at Home
  11. ICML 2026Do Activation Verbalization Methods Convey Privileged Information?
  12. ICML 2026Does a Hybrid Space-Aware Randomized Defense Improve Empirical and Certified Adversarial Robustness?
  13. ICML 2026DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation
  14. ICML 2026DualCOIL: Offline Imitation Learning from Contrasting Demonstrations
  15. ICML 2026Dynamic Linear Attention
  16. ICML 2026Dynamic Multimodal Evaluation via Knowledge-Enhanced Benchmark Evolution
  17. ICML 2026DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents
  18. ICML 2026EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models
  19. ICML 2026Efficient Multi-modal Dataset Distillation via Analytic Parameter Matching
  20. ICML 2026Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets
  21. ICML 2026Empirical Gaussian Processes
  22. ICML 2026Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion Models
  23. ICML 2026Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
  24. ICML 2026Evaluating Language Models in Realistic Conversational Contexts
  25. ICML 2026Evaluating Object-Centric Models beyond Object Discovery
  26. ICML 2026Expanding the AI Evaluation Toolbox with Statistical Models
  27. ICML 2026Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
  28. ICML 2026Exploring 3D Dataset Pruning
  29. ICML 2026FairJudge : An Adaptive, Debiased, and Consistent LLM-as-a-Judge
  30. ICML 2026Falling Trees: A Model Class for Interpretable Risk Prioritization
  31. ICML 2026Fast k-means Seeding Under The Manifold Hypothesis
  32. ICML 2026Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
  33. ICML 2026FedARC: Anchor-Guided Residual Compensation for Data and Model Heterogeneous Federated Learning
  34. ICML 2026Federated Data and Feature Selection by Generalized CUR Decomposition
  35. ICML 2026Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
  36. ICML 2026Fine-Tune Once, Reuse Across Models: Bayesian Task-Update Factors and Approximations
  37. ICML 2026FiX: Introducing Fine-grained Forget Gate into Softmax Attention
  38. ICML 2026Fixed Aggregation Features Can Rival GNNs
  39. ICML 2026FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications
  40. ICML 2026Focus and Dilution: The Multi-stage Learning Process of Attention
  41. ICML 2026Forgetting Whenever You Want: A Decentralized Continual Learning Framework with On-Demand Unlearning
  42. ICML 2026Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks
  43. ICML 2026From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide ML Interatomic Potential Architectures
  44. ICML 2026From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning
  45. ICML 2026FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
  46. ICML 2026Full-Spectrum Graph Neural Networks: Expressive and Scalable
  47. ICML 2026GENEB: Why Genomic Models Are Hard to Compare
  48. ICML 2026Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
  49. ICML 2026GeoDM: Geometry-aware Distribution Matching for Dataset Distillation
  50. ICML 2026Geometric Conformal Prediction with Spatial Ranks and Multivariate Quantiles

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