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 296 篇，第 5 / 6 页

  1. ICML 2024Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters
  2. ICML 2024Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
  3. ICML 2024INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer
  4. ICML 2024Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
  5. ICML 2024Learning to Route Among Specialized Experts for Zero-Shot Generalization
  6. ICML 2024Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
  7. ICML 2024Mixtures of Experts Unlock Parameter Scaling for Deep RL
  8. ICML 2024MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
  9. ICML 2024On Interpolating Experts and Multi-Armed Bandits
  10. ICML 2024On Least Square Estimation in Softmax Gating Mixture of Experts
  11. ICML 2024One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
  12. ICML 2024OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
  13. ICML 2024Receptive Fields As Experts in Convolutional Neural Architectures
  14. ICML 2024Scaling Beyond the GPU Memory Limit for Large Mixture-of-Experts Model Training
  15. ICML 2024Scaling Laws for Fine-Grained Mixture of Experts
  16. ICML 2024See More Details: Efficient Image Super-Resolution by Experts Mining
  17. ICML 2024Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
  18. ICML 2024Theoretical insights for diffusion guidance: A case study for Gaussian mixture models
  19. ICML 2024Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
  20. ICML 2024Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models
  21. ICML 2023A Distribution Optimization Framework for Confidence Bounds of Risk Measures
  22. ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
  23. ICML 2023A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
  24. ICML 2023A theory of continuous generative flow networks
  25. ICML 2023A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates
  26. ICML 2023Active Ranking of Experts Based on their Performances in Many Tasks
  27. ICML 2023Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
  28. ICML 2023Beyond the Edge of Stability via Two-step Gradient Updates
  29. ICML 2023Chemically Transferable Generative Backmapping of Coarse-Grained Proteins
  30. ICML 2023Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator
  31. ICML 2023Computational Doob h-transforms for Online Filtering of Discretely Observed Diffusions
  32. ICML 2023Continuously Parameterized Mixture Models
  33. ICML 2023Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction
  34. ICML 2023Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders
  35. ICML 2023Differentiable Simulations for Enhanced Sampling of Rare Events
  36. ICML 2023Discrete Continuous Optimization Framework for Simultaneous Clustering and Training in Mixture Models
  37. ICML 2023Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction
  38. ICML 2023Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
  39. ICML 2023Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories
  40. ICML 2023End-to-End Multi-Object Detection with a Regularized Mixture Model
  41. ICML 2023Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule
  42. ICML 2023Explaining the effects of non-convergent MCMC in the training of Energy-Based Models
  43. ICML 2023Generative Decoding of Visual Stimuli
  44. ICML 2023Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization
  45. ICML 2023Global Selection of Contrastive Batches via Optimization on Sample Permutations
  46. ICML 2023High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
  47. ICML 2023Identifiability of Label Noise Transition Matrix
  48. ICML 2023Identification of the Adversary from a Single Adversarial Example
  49. ICML 2023Instrumental Variable Estimation of Average Partial Causal Effects
  50. ICML 2023Lifelong Language Pretraining with Distribution-Specialized Experts

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