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 948 篇，第 6 / 19 页

  1. ICML 2026UltraLIF: Fully Differentiable Spiking Neural Networks via Ultradiscretization and Max-Plus Algebra
  2. ICML 2026Uncovering Competency Gaps in Large Language Models and Their Benchmarks
  3. ICML 2026Understanding Data Temporality Impact on Large Language Models Pre-training
  4. ICML 2026Understanding Generalization from Embedding Dimension and Distributional Convergence
  5. ICML 2026Unified Time Series Explanations via Amortized Optimization and Instance-level Multi-Expert Knowledge Distillation
  6. ICML 2026Unifying and Optimizing Data Values for Selection via Sequential Decision-Making
  7. ICML 2026Unifying Dataset Pruning and Distillation for Efficient Large-scale Compression
  8. ICML 2026Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets
  9. ICML 2026UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms
  10. ICML 2026Unlocking the Potential of Continual Model Merging: An ODE Perspective
  11. ICML 2026Unsupervised Camouflaged Object Detection with Dual-Eigenvector Spectral Pseudo-Labeling and Contrastive Refinement
  12. ICML 2026UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems
  13. ICML 2026Utility Boundary of Dataset Distillation: Scaling and Coverage Laws
  14. ICML 2026VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
  15. ICML 2026Vector Linking via Cross-Model Local Isometric Consistency
  16. ICML 2026VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection
  17. ICML 2026WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field Convolution
  18. ICML 2026WeightCLIP: Aligning Datasets and Models for Weight Space Learning
  19. ICML 2026WF-Bench: A Benchmark for Neural-Network WaveFunction Expressivity and Scaling Laws
  20. ICML 2026What Language is This? Ask Your Tokenizer.
  21. ICML 2026When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
  22. ICML 2026When Can We Trust Survival Model Evaluation ?
  23. ICML 2026When Do Diffusion Models Learn to Generate Multiple Objects?
  24. ICML 2026When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs
  25. ICML 2026Why Self-Distillation Helps and Hurts: Denoising vs. Signal Forgetting
  26. ICML 2025A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
  27. ICML 2025A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity
  28. ICML 2025AAAR-1.0: Assessing AI’s Potential to Assist Research
  29. ICML 2025Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$
  30. ICML 2025Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
  31. ICML 2025Active Evaluation Acquisition for Efficient LLM Benchmarking
  32. ICML 2025Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
  33. ICML 2025Adversarial Robustness via Deformable Convolution with Stochasticity
  34. ICML 2025AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
  35. ICML 2025Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
  36. ICML 2025Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery
  37. ICML 2025Approximating Latent Manifolds in Neural Networks via Vanishing Ideals
  38. ICML 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
  39. ICML 2025Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
  40. ICML 2025Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios
  41. ICML 2025Average Sensitivity of Hierarchical $k$-Median Clustering
  42. ICML 2025Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data
  43. ICML 2025Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data
  44. ICML 2025Benign Overfitting in Token Selection of Attention Mechanism
  45. ICML 2025Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination
  46. ICML 2025Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
  47. ICML 2025CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
  48. ICML 2025Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation
  49. ICML 2025Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
  50. ICML 2025Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction

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