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 26 / 118 页

  1. ICML 2026MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
  2. ICML 2026Narrowing the ANN–SNN Gap for Continuous 1D Temporal Signal Classification with Multi-Scale Temporal Encoding and Sparsity-Regularized Transform Encoding
  3. ICML 2026Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0,L_1)$-Smoothness
  4. ICML 2026Needles in the Haystack: Addressing Signal Dilution Improves scRNA-seq Perturbation Response Modeling and Evaluation
  5. ICML 2026Neural Logistic Bandits
  6. ICML 2026NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional Data
  7. ICML 2026New Algorithms for Fully-Dynamic k-center with Outliers
  8. ICML 2026New Bounds for Kernel Sums via Fast Spherical Embeddings
  9. ICML 2026Offline Multi-agent Continual Cooperation via Skill Partition and Reuse
  10. ICML 2026Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment
  11. ICML 2026On the Expressive Power of GNNs to Solve Linear SDPs
  12. ICML 2026One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series Analysis
  13. ICML 2026OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
  14. ICML 2026Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning
  15. ICML 2026ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research
  16. ICML 2026OSM+: Billion-Level Open Street Map Dataset for City-wide Experiments
  17. ICML 2026Per-example Gradients: a New Frontier for Understanding and Improving Optimizers
  18. ICML 2026Plasticity Activation via Polar Operator: A Plug-in Method for Balancing Stability and Plasticity
  19. ICML 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
  20. ICML 2026Positive-Unlabeled Learning with Extreme Scarcity of Labeled Positives
  21. ICML 2026Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
  22. ICML 2026Prioritized Model Experience Replay
  23. ICML 2026PRISM: Demystifying Retention and Interaction in Mid-Training
  24. ICML 2026Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
  25. ICML 2026Probably Approximately Correct Labels
  26. ICML 2026ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation
  27. ICML 2026Progressive Cramming: Reliable Token Compression and What It Reveals
  28. ICML 2026ProMiSE: Protein Multi-State Evaluation Benchmark in Biological Contexts
  29. ICML 2026ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling
  30. ICML 2026ProtDBench: A Unified Benchmark of Protein Binder Design and Evaluation
  31. ICML 2026Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation
  32. ICML 2026QuITE: Query-Based Irregular Time Series Embedding
  33. ICML 2026Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
  34. ICML 2026Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
  35. ICML 2026Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases
  36. ICML 2026Reliable Thinking with Images
  37. ICML 2026Rethinking Contrastive Learning for Graph Collaborative Filtering: Limitations and a Simple Remedy
  38. ICML 2026Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution
  39. ICML 2026Rethinking Multimodal Time-Series Forecasting Evaluation
  40. ICML 2026Rethinking Personalization in Large Language Models at the Token Level
  41. ICML 2026Revisiting Distribution Correction Estimation for Offline Imitation Learning with Suboptimal Dataset
  42. ICML 2026Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
  43. ICML 2026Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
  44. ICML 2026Revisiting the Volume Hypothesis
  45. ICML 2026Richer Bayesian Last Layers with Subsampled NTK Features
  46. ICML 2026Riemannian Neural Optimal Transport
  47. ICML 2026RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models
  48. ICML 2026ROAMM: A Benchmark Dataset for Multimodal Human Attention Decoding and EEG-to-Text Modeling During Naturalistic Reading
  49. ICML 2026Routing and Reasoned Evaluation with Large Language Models
  50. ICML 2026RubricRobustness: Evaluating the Sensitivity of Rubrics-Based Benchmarks to Simple Perturbations

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