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 904 篇，第 14 / 19 页

  1. NeurIPS 2024Neural Experts: Mixture of Experts for Implicit Neural Representations
  2. NeurIPS 2024Non-Euclidean Mixture Model for Social Network Embedding
  3. NeurIPS 2024Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge
  4. NeurIPS 2024Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
  5. NeurIPS 2024Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning
  6. NeurIPS 2024ProxyFusion: Face Feature Aggregation Through Sparse Experts
  7. NeurIPS 2024Robust Mixture Learning when Outliers Overwhelm Small Groups
  8. NeurIPS 2024Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
  9. NeurIPS 2024Smoothie: Label Free Language Model Routing
  10. NeurIPS 2024Spiking Transformer with Experts Mixture
  11. NeurIPS 2024Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
  12. NeurIPS 2024SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
  13. NeurIPS 2024Toward Efficient Inference for Mixture of Experts
  14. NeurIPS 2024Transcendence: Generative Models Can Outperform The Experts That Train Them
  15. NeurIPS 2024Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
  16. NeurIPS 2024Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast
  17. NeurIPS 2024Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
  18. NeurIPS 2024Variational Distillation of Diffusion Policies into Mixture of Experts
  19. CVPR 2023Balanced Product of Calibrated Experts for Long-Tailed Recognition
  20. CVPR 2023ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts
  21. CVPR 2023Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions
  22. CVPR 2023MixNeRF: Modeling a Ray With Mixture Density for Novel View Synthesis From Sparse Inputs
  23. CVPR 2023Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners
  24. CVPR 2023RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction
  25. ICLR 2023A Mixture-of-Expert Approach to RL-based Dialogue Management
  26. ICLR 2023Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization
  27. ICLR 2023DINO as a von Mises-Fisher mixture model
  28. ICLR 2023Impossibly Good Experts and How to Follow Them
  29. ICLR 2023Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models
  30. ICLR 2023Learning About Progress From Experts
  31. ICLR 2023Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition
  32. ICLR 2023Learning to CROSS exchange to solve min-max vehicle routing problems
  33. ICLR 2023Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts
  34. ICLR 2023SCoMoE: Efficient Mixtures of Experts with Structured Communication
  35. ICLR 2023Sparse Mixture-of-Experts are Domain Generalizable Learners
  36. ICLR 2023Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
  37. ICLR 2023Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints
  38. ICLR 2023Sparsity-Constrained Optimal Transport
  39. ICLR 2023Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields
  40. ICLR 2023Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
  41. ICML 2023A Distribution Optimization Framework for Confidence Bounds of Risk Measures
  42. ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
  43. ICML 2023A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
  44. ICML 2023A theory of continuous generative flow networks
  45. ICML 2023A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates
  46. ICML 2023Active Ranking of Experts Based on their Performances in Many Tasks
  47. ICML 2023Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
  48. ICML 2023Beyond the Edge of Stability via Two-step Gradient Updates
  49. ICML 2023Chemically Transferable Generative Backmapping of Coarse-Grained Proteins
  50. ICML 2023Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator

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