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 23 / 118 页

  1. ICML 2026ActiveScope: Actively Seeking and Correcting Perception for MLLMs
  2. ICML 2026Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks
  3. ICML 2026AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems
  4. ICML 2026Align Your Trajectory Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
  5. ICML 2026Ambient Dataloops: Generative Models for Dataset Refinement
  6. ICML 2026Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
  7. ICML 2026An Evidential Route to Asymptotic Bayes Optimality under Sparsity
  8. ICML 2026An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
  9. ICML 2026Analytic Bijections for Smooth and Interpretable Normalizing Flows
  10. ICML 2026Approximation Error Upper and Lower Bounds for Hölder Class with Transformers
  11. ICML 2026Arboreal Neural Network
  12. ICML 2026Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach
  13. ICML 2026Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation?
  14. ICML 2026Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses
  15. ICML 2026Attention Hijacking: Backdooring Text Dataset Distillation via Semantic Anchors
  16. ICML 2026AutoBaxBuilder: Bootstrapping Code Security Benchmarking
  17. ICML 2026BASIL: Scalable Bayesian Semi-supervised Clustering with Feature Selection and Adaptive Constraint Weighting
  18. ICML 2026BEAR: Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis
  19. ICML 2026BEST: Benchmarking Efficiency in Space and Time for LLM-Generated Code
  20. ICML 2026Beyond Benchmarks: Toward Causally Faithful Evaluation of Large Language Models
  21. ICML 2026Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
  22. ICML 2026Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors
  23. ICML 2026Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
  24. ICML 2026Biased Generalization in Diffusion Models
  25. ICML 2026Bits That Count: Quantifying and Predicting Capabilities of Language Models
  26. ICML 2026Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models
  27. ICML 2026Bridging Spherical Black-Box Optimizers
  28. ICML 2026Bridging the Gap Between Average and Discounted TD Learning
  29. ICML 2026Calibrated Multimodal Representation Learning with Missing Modalities
  30. ICML 2026CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
  31. ICML 2026Causal Identification from Counterfactual Data: Completeness and Bounding Results
  32. ICML 2026Causes and Consequences of Representational Similarity in Machine Learning Models
  33. ICML 2026Certifying Graph Neural Networks Against Label and Structure Poisoning
  34. ICML 2026CHB: A Diagnostic Toolkit for Hardness-Aware Clustering Evaluation
  35. ICML 2026Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
  36. ICML 2026Connecting Independently Trained Modes via Layer-Wise Connectivity
  37. ICML 2026Convex Dataset Valuation for Post-Training
  38. ICML 2026Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation
  39. ICML 2026Cooperative Variance Estimation and Bayesian Neural Networks for Disentangling Aleatoric and Epistemic Uncertainties
  40. ICML 2026Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
  41. ICML 2026Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
  42. ICML 2026Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
  43. ICML 2026CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
  44. ICML 2026CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM
  45. ICML 2026Curating the Future: A Scalable Recipe for Training Open-Ended Forecasters
  46. ICML 2026Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
  47. ICML 2026DataGuard: A Non-intrusive Dataset Auditing Framework via Differential Information Forensics
  48. ICML 2026Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation
  49. ICML 2026Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator Trees
  50. ICML 2026Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training

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