混合专家论文趋势 2023–2026

MoE 路由与训练

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 904 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

混合专家论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202313816766236
20245524319119
202586595721223
2026757313246326

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

全部混合专家论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 354 篇，第 7 / 8 页

  1. NeurIPS 2023On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection
  2. NeurIPS 2023On the Size and Approximation Error of Distilled Datasets
  3. NeurIPS 2023On the Variance, Admissibility, and Stability of Empirical Risk Minimization
  4. NeurIPS 2023One-step differentiation of iterative algorithms
  5. NeurIPS 2023Opening the Vocabulary of Egocentric Actions
  6. NeurIPS 2023Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection
  7. NeurIPS 2023Optimization of Inter-group criteria for clustering with minimum size constraints
  8. NeurIPS 2023Persuading Farsighted Receivers in MDPs: the Power of Honesty
  9. NeurIPS 2023PoET: A generative model of protein families as sequences-of-sequences
  10. NeurIPS 2023Predict-then-Calibrate: A New Perspective of Robust Contextual LP
  11. NeurIPS 2023Private estimation algorithms for stochastic block models and mixture models
  12. NeurIPS 2023Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond
  13. NeurIPS 2023Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
  14. NeurIPS 2023RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
  15. NeurIPS 2023Reconciling Competing Sampling Strategies of Network Embedding
  16. NeurIPS 2023Regularization properties of adversarially-trained linear regression
  17. NeurIPS 2023Representational Strengths and Limitations of Transformers
  18. NeurIPS 2023Reproducibility study of 'Proto2Proto: Can you recognise the car, the way I do?'
  19. NeurIPS 2023Reproducibility Study of ”CartoonX: Cartoon Explanations of Image Classifiers”
  20. NeurIPS 2023Reproducibility Study of “Quantifying Societal Bias Amplification in Image Captioning”
  21. NeurIPS 2023Rigorous Runtime Analysis of MOEA/D for Solving Multi-Objective Minimum Weight Base Problems
  22. NeurIPS 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
  23. NeurIPS 2023Sample Complexity of Forecast Aggregation
  24. NeurIPS 2023Self-Consistent Velocity Matching of Probability Flows
  25. NeurIPS 2023SHAP-IQ: Unified Approximation of any-order Shapley Interactions
  26. NeurIPS 2023Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms
  27. NeurIPS 2023ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
  28. NeurIPS 2023SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions
  29. NeurIPS 2023Sparse Modular Activation for Efficient Sequence Modeling
  30. NeurIPS 2023Stable Vectorization of Multiparameter Persistent Homology using Signed Barcodes as Measures
  31. NeurIPS 2023Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows
  32. NeurIPS 2023Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
  33. NeurIPS 2023Sub-optimality of the Naive Mean Field approximation for proportional high-dimensional Linear Regression
  34. NeurIPS 2023The Adversarial Consistency of Surrogate Risks for Binary Classification
  35. NeurIPS 2023The Behavior and Convergence of Local Bayesian Optimization
  36. NeurIPS 2023The Distortion of Binomial Voting Defies Expectation
  37. NeurIPS 2023The emergence of clusters in self-attention dynamics
  38. NeurIPS 2023The Grand Illusion: The Myth of Software Portability and Implications for ML Progress.
  39. NeurIPS 2023The Impact of Positional Encoding on Length Generalization in Transformers
  40. NeurIPS 2023The Separation Capacity of Random Neural Networks
  41. NeurIPS 2023Towards a fuller understanding of neurons with Clustered Compositional Explanations
  42. NeurIPS 2023Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent
  43. NeurIPS 2023Train 'n Trade: Foundations of Parameter Markets
  44. NeurIPS 2023Training Chain-of-Thought via Latent-Variable Inference
  45. NeurIPS 2023Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete
  46. NeurIPS 2023Training neural operators to preserve invariant measures of chaotic attractors
  47. NeurIPS 2023Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory
  48. NeurIPS 2023Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
  49. NeurIPS 2023Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy
  50. NeurIPS 2023Utilitarian Algorithm Configuration

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 查混合专家在 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": "mixture-of-experts"}

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混合专家论文？
共 904 篇，按年份分别是 2023 年 236 篇、2024 年 119 篇、2025 年 223 篇、2026 年 326 篇。
NeurIPS 2026 有多少篇混合专家论文？
NeurIPS 2026 有 75 篇混合专家论文，上一届是 86 篇。
ICLR 2026 有多少篇混合专家论文？
ICLR 2026 有 73 篇混合专家论文，上一届是 59 篇。
ICML 2026 有多少篇混合专家论文？
ICML 2026 有 132 篇混合专家论文，上一届是 57 篇。
CVPR 2026 有多少篇混合专家论文？
CVPR 2026 有 46 篇混合专家论文，上一届是 21 篇。
哪个会议的混合专家论文最多？
NeurIPS，2023–2026 年共 354 篇。

「优化与缩放」下的其他主题