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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 138 | 16 | 76 | 6 | 236 |
| 2024 | 55 | 24 | 31 | 9 | 119 |
| 2025 | 86 | 59 | 57 | 21 | 223 |
| 2026 | 75 | 73 | 132 | 46 | 326 |
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 5 / 5 页
- NeurIPS 2025On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks
- NeurIPS 2025Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making
- NeurIPS 2025Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
- NeurIPS 2025PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
- NeurIPS 2025Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
- NeurIPS 2025RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
- NeurIPS 2025Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
- NeurIPS 2025S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
- NeurIPS 2025Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins
- NeurIPS 2025Soft Task-Aware Routing of Experts for Equivariant Representation Learning
- NeurIPS 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
- NeurIPS 2025Symmetry-Preserving Conformer Ensemble Networks for Molecular Representation Learning
- NeurIPS 2025TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
- NeurIPS 2025The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model
- NeurIPS 2025The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model
- NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
- NeurIPS 2025Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
- NeurIPS 2025Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
- NeurIPS 2025UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification
- NeurIPS 2025UMoE: Unifying Attention and FFN with Shared Experts
- NeurIPS 2025Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework
- NeurIPS 2025Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts
- NeurIPS 2025Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
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"}
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。