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 7 / 19 页

  1. ICML 2025CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models
  2. ICML 2025Clustering Properties of Self-Supervised Learning
  3. ICML 2025CoastalBench: A Decade-Long High-Resolution Dataset to Emulate Complex Coastal Processes
  4. ICML 2025Communicating Activations Between Language Model Agents
  5. ICML 2025Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
  6. ICML 2025Concentration Distribution Learning from Label Distributions
  7. ICML 2025Concept Reachability in Diffusion Models: Beyond Dataset Constraints
  8. ICML 2025Conservative Offline Goal-Conditioned Implicit V-Learning
  9. ICML 2025Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion
  10. ICML 2025CoSER: Coordinating LLM-Based Persona Simulation of Established Roles
  11. ICML 2025Counterfactual Voting Adjustment for Quality Assessment and Fairer Voting in Online Platforms with Helpfulness Evaluation
  12. ICML 2025CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
  13. ICML 2025CTBench: A Library and Benchmark for Certified Training
  14. ICML 2025DataDecide: How to Predict Best Pretraining Data with Small Experiments
  15. ICML 2025Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making
  16. ICML 2025Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
  17. ICML 2025Diverging Preferences: When do Annotators Disagree and do Models Know?
  18. ICML 2025Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
  19. ICML 2025Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training
  20. ICML 2025Don't Restart, Just Reuse: Reoptimizing MILPs with Dynamic Parameters
  21. ICML 2025EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification
  22. ICML 2025EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction
  23. ICML 2025Efficient Core-set Selection for Deep Learning Through Squared Loss Minimization
  24. ICML 2025Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset Distillation
  25. ICML 2025Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
  26. ICML 2025Enhancing Spectral GNNs: From Topology and Perturbation Perspectives
  27. ICML 2025Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
  28. ICML 2025FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees
  29. ICML 2025Faster Approximation Algorithms for k-Center via Data Reduction
  30. ICML 2025FG-CLIP: Fine-Grained Visual and Textual Alignment
  31. ICML 2025Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
  32. ICML 2025From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline
  33. ICML 2025Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks
  34. ICML 2025GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras
  35. ICML 2025Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\mu$ Parametrization
  36. ICML 2025Gradient Boosting Reinforcement Learning
  37. ICML 2025Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres
  38. ICML 2025Heterogeneous Label Shift: Theory and Algorithm
  39. ICML 2025Hierarchical Overlapping Clustering on Graphs: Cost Function, Algorithm and Scalability
  40. ICML 2025Hierarchical Refinement: Optimal Transport to Infinity and Beyond
  41. ICML 2025How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence
  42. ICML 2025How to set AdamW's weight decay as you scale model and dataset size
  43. ICML 2025Identifiable Object Representations under Spatial Ambiguities
  44. ICML 2025Idiosyncrasies in Large Language Models
  45. ICML 2025Implicit Language Models are RNNs: Balancing Parallelization and Expressivity
  46. ICML 2025Impossible Videos
  47. ICML 2025Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions
  48. ICML 2025Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
  49. ICML 2025Improving the Effective Receptive Field of Message-Passing Neural Networks
  50. ICML 2025Independence Tests for 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