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 189 篇，第 4 / 4 页

  1. ICML 2025Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants
  2. ICML 2025SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
  3. ICML 2025Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
  4. ICML 2025SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
  5. ICML 2025SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
  6. ICML 2025SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services
  7. ICML 2025Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
  8. ICML 2025Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
  9. ICML 2025Stable Offline Value Function Learning with Bisimulation-based Representations
  10. ICML 2025STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
  11. ICML 2025Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
  12. ICML 2025TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems
  13. ICML 2025TabSDS: a Lightweight, Fully Non-Parametric, and Model Free Approach for Generating Synthetic Tabular Data
  14. ICML 2025Taming Diffusion for Dataset Distillation with High Representativeness
  15. ICML 2025TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion
  16. ICML 2025The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
  17. ICML 2025The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination
  18. ICML 2025The Power of Random Features and the Limits of Distribution-Free Gradient Descent
  19. ICML 2025The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
  20. ICML 2025The Underlying Universal Statistical Structure of Natural Datasets
  21. ICML 2025Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset
  22. ICML 2025Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
  23. ICML 2025Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer
  24. ICML 2025Training Software Engineering Agents and Verifiers with SWE-Gym
  25. ICML 2025Trajectory World Models for Heterogeneous Environments
  26. ICML 2025Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries
  27. ICML 2025Understanding Fixed Predictions via Confined Regions
  28. ICML 2025Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
  29. ICML 2025Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach
  30. ICML 2025Unlocking Post-hoc Dataset Inference with Synthetic Data
  31. ICML 2025Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
  32. ICML 2025Unpaired Point Cloud Completion via Unbalanced Optimal Transport
  33. ICML 2025Unsupervised Learning for Class Distribution Mismatch
  34. ICML 2025When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration
  35. ICML 2025When, Where and Why to Average Weights?
  36. ICML 2025Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
  37. ICML 2025WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
  38. ICML 2025WorldSimBench: Towards Video Generation Models as World Simulators
  39. ICML 2025ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

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