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 904 篇，第 11 / 19 页

501. NeurIPS 2025Localist Topographic Expert Routing: A Barrel Cortex-Inspired Modular Network for Sensorimotor Processing
502. NeurIPS 2025Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation
503. NeurIPS 2025Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training
504. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
505. NeurIPS 2025MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
506. NeurIPS 2025Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
507. NeurIPS 2025Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
508. NeurIPS 2025Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
509. NeurIPS 2025Mixture-of-Experts Meets In-Context Reinforcement Learning
510. NeurIPS 2025Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
511. NeurIPS 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
512. NeurIPS 2025MoBA: Mixture of Block Attention for Long-Context LLMs
513. NeurIPS 2025Model Merging in Pre-training of Large Language Models
514. NeurIPS 2025MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
515. NeurIPS 2025MoE-Gyro: Self-Supervised Over-Range Reconstruction and Denoising for MEMS Gyroscopes
516. NeurIPS 2025MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning
517. NeurIPS 2025MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
518. NeurIPS 2025MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
519. NeurIPS 2025MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding
520. NeurIPS 2025Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
521. NeurIPS 2025Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
522. NeurIPS 2025Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
523. NeurIPS 2025No Experts, No Problem: Avoidance Learning from Bad Demonstrations
524. NeurIPS 2025Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
525. NeurIPS 2025On Linear Mode Connectivity of Mixture-of-Experts Architectures
526. NeurIPS 2025On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
527. NeurIPS 2025On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks
528. NeurIPS 2025Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making
529. NeurIPS 2025Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
530. NeurIPS 2025PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
531. NeurIPS 2025Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
532. NeurIPS 2025RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
533. NeurIPS 2025Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
534. NeurIPS 2025S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
535. NeurIPS 2025Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins
536. NeurIPS 2025Soft Task-Aware Routing of Experts for Equivariant Representation Learning
537. NeurIPS 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
538. NeurIPS 2025Symmetry-Preserving Conformer Ensemble Networks for Molecular Representation Learning
539. NeurIPS 2025TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
540. NeurIPS 2025The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model
541. NeurIPS 2025The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model
542. NeurIPS 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
543. NeurIPS 2025Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
544. NeurIPS 2025Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
545. NeurIPS 2025UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification
546. NeurIPS 2025UMoE: Unifying Attention and FFN with Shared Experts
547. NeurIPS 2025Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework
548. NeurIPS 2025Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts
549. NeurIPS 2025Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
550. CVPR 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

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。