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 223 篇，第 1 / 5 页

1. CVPR 2025CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
2. CVPR 2025CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework
3. CVPR 2025Complexity Experts are Task-Discriminative Learners for Any Image Restoration
4. CVPR 2025DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
5. CVPR 2025dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis
6. CVPR 2025Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
7. CVPR 2025EMOE: Modality-Specific Enhanced Dynamic Emotion Experts
8. CVPR 2025Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
9. CVPR 2025Learning Heterogeneous Tissues with Mixture of Experts for Gigapixel Whole Slide Images
10. CVPR 2025Learning on Model Weights using Tree Experts
11. CVPR 2025Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
12. CVPR 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes
13. CVPR 2025Mixture of Submodules for Domain Adaptive Person Search
14. CVPR 2025MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation
15. CVPR 2025MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
16. CVPR 2025Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset
17. CVPR 2025pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation
18. CVPR 2025Question-Aware Gaussian Experts for Audio-Visual Question Answering
19. CVPR 2025Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning
20. CVPR 2025SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking
21. CVPR 2025V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts
22. ICLR 2025A Sanity Check for AI-generated Image Detection
23. ICLR 2025Ada-K Routing: Boosting the Efficiency of MoE-based LLMs
24. ICLR 2025Balancing Act: Diversity and Consistency in Large Language Model Ensembles
25. ICLR 2025BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
26. ICLR 2025CAMEx: Curvature-aware Merging of Experts
27. ICLR 2025Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference
28. ICLR 2025Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
29. ICLR 2025Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
30. ICLR 2025Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
31. ICLR 2025Dynamic Modeling of Patients, Modalities and Tasks via Multi-modal Multi-task Mixture of Experts
32. ICLR 2025Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
33. ICLR 2025EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing
34. ICLR 2025Efficient Dictionary Learning with Switch Sparse Autoencoders
35. ICLR 2025Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
36. ICLR 2025Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping
37. ICLR 2025Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts
38. ICLR 2025ELBOing Stein: Variational Bayes with Stein Mixture Inference
39. ICLR 2025End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler
40. ICLR 2025Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
41. ICLR 2025Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models
42. ICLR 2025Gaussian Mixture Counterfactual Generator
43. ICLR 2025Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors
44. ICLR 2025GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks
45. ICLR 2025Graph Sparsification via Mixture of Graphs
46. ICLR 2025HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA Experts
47. ICLR 2025Intrinsic User-Centric Interpretability through Global Mixture of Experts
48. ICLR 2025Layerwise Recurrent Router for Mixture-of-Experts
49. ICLR 2025Many-Objective Multi-Solution Transport
50. ICLR 2025Mixture Compressor for Mixture-of-Experts LLMs Gains More

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。