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 10 / 19 页

451. ICML 2025Parrot: Multilingual Visual Instruction Tuning
452. ICML 2025Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
453. ICML 2025QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
454. ICML 2025R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts
455. ICML 2025RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts
456. ICML 2025Retraining-free Merging of Sparse MoE via Hierarchical Clustering
457. ICML 2025Scaling Laws for Upcycling Mixture-of-Experts Language Models
458. ICML 2025Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions
459. ICML 2025Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts
460. ICML 2025Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
461. ICML 2025SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
462. ICML 2025TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision
463. ICML 2025What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning
464. NeurIPS 2025A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random
465. NeurIPS 2025Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning
466. NeurIPS 2025Advancing Expert Specialization for Better MoE
467. NeurIPS 2025ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation
468. NeurIPS 2025Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
469. NeurIPS 2025Brain-Like Processing Pathways Form in Models With Heterogeneous Experts
470. NeurIPS 2025BrainMoE: Cognition Joint Embedding via Mixture-of-Expert Towards Robust Brain Foundation Model
471. NeurIPS 2025Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models
472. NeurIPS 2025Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation
473. NeurIPS 2025CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
474. NeurIPS 2025Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
475. NeurIPS 2025Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
476. NeurIPS 2025Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
477. NeurIPS 2025DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
478. NeurIPS 2025Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective
479. NeurIPS 2025Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
480. NeurIPS 2025Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data
481. NeurIPS 2025Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations
482. NeurIPS 2025Enhanced Expert Merging for Mixture-of-Experts in Graph Foundation Models
483. NeurIPS 2025Evaluating multiple models using labeled and unlabeled data
484. NeurIPS 2025FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression
485. NeurIPS 2025Fisher meets Feynman: score-based variational inference with a product of experts
486. NeurIPS 2025FlashMoE: Fast Distributed MoE in a Single Kernel
487. NeurIPS 2025FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training
488. NeurIPS 2025FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
489. NeurIPS 2025Gate to the Vessel: Residual Experts Restore What SAM Overlooks
490. NeurIPS 2025Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
491. NeurIPS 2025Geometric Mixture Models for Electrolyte Conductivity Prediction
492. NeurIPS 2025Go With the Flow: Fast Diffusion for Gaussian Mixture Models
493. NeurIPS 2025HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
494. NeurIPS 2025HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts
495. NeurIPS 2025Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning
496. NeurIPS 2025LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
497. NeurIPS 2025Learning Expandable and Adaptable Representations for Continual Learning
498. NeurIPS 2025Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
499. NeurIPS 2025Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
500. NeurIPS 2025Linear Mixture Distributionally Robust Markov Decision Processes

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。