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 4 / 5 页

151. NeurIPS 2025DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
152. NeurIPS 2025Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective
153. NeurIPS 2025Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
154. NeurIPS 2025Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data
155. NeurIPS 2025Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations
156. NeurIPS 2025Enhanced Expert Merging for Mixture-of-Experts in Graph Foundation Models
157. NeurIPS 2025Evaluating multiple models using labeled and unlabeled data
158. NeurIPS 2025FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression
159. NeurIPS 2025Fisher meets Feynman: score-based variational inference with a product of experts
160. NeurIPS 2025FlashMoE: Fast Distributed MoE in a Single Kernel
161. NeurIPS 2025FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training
162. NeurIPS 2025FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
163. NeurIPS 2025Gate to the Vessel: Residual Experts Restore What SAM Overlooks
164. NeurIPS 2025Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
165. NeurIPS 2025Geometric Mixture Models for Electrolyte Conductivity Prediction
166. NeurIPS 2025Go With the Flow: Fast Diffusion for Gaussian Mixture Models
167. NeurIPS 2025HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
168. NeurIPS 2025HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts
169. NeurIPS 2025Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning
170. NeurIPS 2025LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
171. NeurIPS 2025Learning Expandable and Adaptable Representations for Continual Learning
172. NeurIPS 2025Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
173. NeurIPS 2025Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
174. NeurIPS 2025Linear Mixture Distributionally Robust Markov Decision Processes
175. NeurIPS 2025Localist Topographic Expert Routing: A Barrel Cortex-Inspired Modular Network for Sensorimotor Processing
176. NeurIPS 2025Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation
177. NeurIPS 2025Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training
178. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
179. NeurIPS 2025MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
180. NeurIPS 2025Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
181. NeurIPS 2025Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
182. NeurIPS 2025Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
183. NeurIPS 2025Mixture-of-Experts Meets In-Context Reinforcement Learning
184. NeurIPS 2025Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
185. NeurIPS 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
186. NeurIPS 2025MoBA: Mixture of Block Attention for Long-Context LLMs
187. NeurIPS 2025Model Merging in Pre-training of Large Language Models
188. NeurIPS 2025MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
189. NeurIPS 2025MoE-Gyro: Self-Supervised Over-Range Reconstruction and Denoising for MEMS Gyroscopes
190. NeurIPS 2025MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning
191. NeurIPS 2025MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
192. NeurIPS 2025MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
193. NeurIPS 2025MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
194. NeurIPS 2025Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
195. NeurIPS 2025Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
196. NeurIPS 2025Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
197. NeurIPS 2025No Experts, No Problem: Avoidance Learning from Bad Demonstrations
198. NeurIPS 2025Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
199. NeurIPS 2025On Linear Mode Connectivity of Mixture-of-Experts Architectures
200. NeurIPS 2025On Minimax Estimation of Parameters in Softmax-Contaminated 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。