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 25 / 118 页

  1. ICML 2026Geometry-Aware Dataset Condensation for Diffusion Model Training
  2. ICML 2026Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models
  3. ICML 2026GFedCL: Graph-Based Federated Continual Learning with Spatial and Temporal Awareness
  4. ICML 2026Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings
  5. ICML 2026Graph Neural Dynamics via Learned Energy and Tangential Flows
  6. ICML 2026Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift
  7. ICML 2026Hedging on the Frontier: Learning New Tasks with Few Samples
  8. ICML 2026HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation
  9. ICML 2026HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
  10. ICML 2026How Can Mamba Learn In Context with Outliers and Generalize Provably?
  11. ICML 2026How much can language models memorize?
  12. ICML 2026How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability
  13. ICML 2026How to Correctly Report LLM-as-a-Judge Evaluations
  14. ICML 2026How to Price Data: A Market Equilibrium Based Approach
  15. ICML 2026Hyperbolic Multimodal Continual Learning
  16. ICML 2026IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension
  17. ICML 2026IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research
  18. ICML 2026Improved Bounds for Reward-Agnostic and Reward-Free Exploration
  19. ICML 2026Influence-Disentangled Federated Training: Learning Models That Are Easy to Unlearn
  20. ICML 2026InfraRL: A Benchmark for Constrained Resource Allocation in Large-Scale Infrastructure Asset Management
  21. ICML 2026Instance-Level Costs for Nuanced Classifier Evaluation
  22. ICML 2026Integrated Episodic and Semantic Memory via Modulating Transformer FeedForward Layers
  23. ICML 2026Interpretable Self-Supervised Learning via Representer Landmarks and Nyström Approximation
  24. ICML 2026Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks
  25. ICML 2026Is Graph Mixup Beneficial? Investigating Interpolation And Empirical Performance of Graph Mixup Methods
  26. ICML 2026It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks
  27. ICML 2026L-CUBE: Isolating Long-Context Capacity from Knowledge with Controllable Mutual Information Scaling
  28. ICML 2026LAMP: Data-Efficient Linear Affine Weight-Space Models for Parameter-Controlled 3D Shape Generation and Extrapolation
  29. ICML 2026Learning Dynamic Stability Landscapes in Synchronization Networks
  30. ICML 2026Learning Flexible Generalization in Video Quality Assessment by Bringing Device and Viewing Condition Distributions
  31. ICML 2026Learning Junta Distributions, Quantum Junta States, and QAC$^0$ Circuits
  32. ICML 2026Learning Partial Concept Classes and Universal Rates Under Massart Noise
  33. ICML 2026Learning Permutation Distributions via Reflected Diffusion on Ranks
  34. ICML 2026Learning syntax without semantics: Disentangled tiny language models
  35. ICML 2026Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation
  36. ICML 2026Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases
  37. ICML 2026LiveNewsBench: Evaluating Web Search Agents with Freshly Curated News
  38. ICML 2026LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate Descent
  39. ICML 2026Magnitude Distance: A Geometric Measure of Dataset Similarity
  40. ICML 2026MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
  41. ICML 2026Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments
  42. ICML 2026Markov Chain Monte Carlo without Evaluating the Target: an Auxiliary Variable Approach
  43. ICML 2026Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
  44. ICML 2026Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
  45. ICML 2026MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
  46. ICML 2026Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching
  47. ICML 2026MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs
  48. ICML 2026MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue
  49. ICML 2026Modeling Attributional Style at Scale: A Dataset and Analysis for Psychological Attribution Assessment and Reframing
  50. ICML 2026MORE: A Multilingual Document Parsing Benchmark and Evaluation

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