混合专家论文趋势 2023–2026

主要结论

• 混合专家论文从 2023 年的 236 篇增长到 2026 年的 326 篇，三年间扩大到约 1.4 倍。
• NeurIPS 是发混合专家论文最多的会议，2023–2026 年共 354 篇，占四个会议总量的 39%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 79 篇。
• 在「优化与缩放」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的缩放定律是 4.1 倍，混合专家是 1.4 倍。

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

• NeurIPS 2026A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution
• ICML 2026$\phi$-Balancing for Mixture-of-Experts Training
• ICLR 2026A Federated Generalized Expectation-Maximization Algorithm for Mixture Models with an Unknown Number of Components
• CVPR 2026Divide Conquer and Aggregate Asymmetric Experts for Class-Imbalanced Semi-Supervised Medical
• NeurIPS 2025Advancing Expert Specialization for Better MoE
• ICML 2025$\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts
• ICLR 2025A Sanity Check for AI-generated Image Detection
• CVPR 2025Complexity Experts are Task-Discriminative Learners for Any Image Restoration
• NeurIPS 2024$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild
• ICML 2024$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
• ICLR 2024Fusing Models with Complementary Expertise
• CVPR 2024MoDE: CLIP Data Experts via Clustering
• NeurIPS 2023[Re] Numerical influence of ReLU'(0) on backpropagation
• ICML 2023A Distribution Optimization Framework for Confidence Bounds of Risk Measures
• ICLR 2023Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models
• CVPR 2023Balanced Product of Calibrated Experts for Long-Tailed Recognition
• NeurIPS 2026AdERA: Adaptive Exponent Reuse for Lossless Allgather in Sharded MoE Training
• ICML 2026Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
• ICLR 2026Abstracting Robot Manipulation Skills via Mixture-of-Experts Diffusion Policies
• CVPR 2026ERMoE Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization

全部混合专家论文

共 119 篇，第 1 / 3 页

1. CVPR 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
2. CVPR 2024GART: Gaussian Articulated Template Models
3. CVPR 2024Language-driven All-in-one Adverse Weather Removal
4. CVPR 2024MoDE: CLIP Data Experts via Clustering
5. CVPR 2024Multi-Task Dense Prediction via Mixture of Low-Rank Experts
6. CVPR 2024OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers
7. CVPR 2024Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts
8. CVPR 2024Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture
9. CVPR 2024Task-Customized Mixture of Adapters for General Image Fusion
10. ICLR 2024Chain-of-Experts: When LLMs Meet Complex Operations Research Problems
11. ICLR 2024Divide and not forget: Ensemble of selectively trained experts in Continual Learning
12. ICLR 2024From Sparse to Soft Mixtures of Experts
13. ICLR 2024Fusing Models with Complementary Expertise
14. ICLR 2024High-dimensional SGD aligns with emerging outlier eigenspaces
15. ICLR 2024Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
16. ICLR 2024Hybrid Sharing for Multi-Label Image Classification
17. ICLR 2024Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
18. ICLR 2024Learning with Mixture of Prototypes for Out-of-Distribution Detection
19. ICLR 2024M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering
20. ICLR 2024Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
21. ICLR 2024Mixture of LoRA Experts
22. ICLR 2024Mixture of Weak and Strong Experts on Graphs
23. ICLR 2024Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models
24. ICLR 2024Object-Centric Learning with Slot Mixture Module
25. ICLR 2024Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
26. ICLR 2024Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
27. ICLR 2024Scaling physics-informed hard constraints with mixture-of-experts
28. ICLR 2024Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
29. ICLR 2024Sparse MoE with Language Guided Routing for Multilingual Machine Translation
30. ICLR 2024Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
31. ICLR 2024Subtractive Mixture Models via Squaring: Representation and Learning
32. ICLR 2024TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
33. ICLR 2024Transformers can optimally learn regression mixture models
34. ICML 2024$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
35. ICML 2024A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts
36. ICML 2024A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)
37. ICML 2024A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
38. ICML 2024Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts
39. ICML 2024Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
40. ICML 2024BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
41. ICML 2024Convergence of Online Learning Algorithm for a Mixture of Multiple Linear Regressions
42. ICML 2024Efficient Mixture Learning in Black-Box Variational Inference
43. ICML 2024Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
44. ICML 2024Exploring the Benefit of Activation Sparsity in Pre-training
45. ICML 2024Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters
46. ICML 2024Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
47. ICML 2024INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer
48. ICML 2024Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
49. ICML 2024Learning to Route Among Specialized Experts for Zero-Shot Generalization
50. ICML 2024Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

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。