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 236 篇，第 2 / 5 页

51. ICML 2023Instrumental Variable Estimation of Average Partial Causal Effects
52. ICML 2023Lifelong Language Pretraining with Distribution-Specialized Experts
53. ICML 2023Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks
54. ICML 2023Mimetic Initialization of Self-Attention Layers
55. ICML 2023Minimax estimation of discontinuous optimal transport maps: The semi-discrete case
56. ICML 2023Mixture Proportion Estimation Beyond Irreducibility
57. ICML 2023Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
58. ICML 2023Neural networks trained with SGD learn distributions of increasing complexity
59. ICML 2023Neural signature kernels as infinite-width-depth-limits of controlled ResNets
60. ICML 2023Non-asymptotic Properties of Individualized Treatment Rules from Sequentially Rule-Adaptive Trials
61. ICML 2023On Distribution Dependent Sub-Logarithmic Query Time of Learned Indexing
62. ICML 2023On Excess Mass Behavior in Gaussian Mixture Models with Orlicz-Wasserstein Distances
63. ICML 2023On Generalizations of Some Distance Based Classifiers for HDLSS Data
64. ICML 2023On the Convergence Rates of Policy Gradient Methods
65. ICML 2023On the Estimation of Gaussian Mixture Copula Models
66. ICML 2023On the Impact of Algorithmic Recourse on Social Segregation
67. ICML 2023On the Robustness of Randomized Ensembles to Adversarial Perturbations
68. ICML 2023On the Within-Group Fairness of Screening Classifiers
69. ICML 2023Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
70. ICML 2023Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
71. ICML 2023Out-of-Domain Robustness via Targeted Augmentations
72. ICML 2023Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
73. ICML 2023Personalized Federated Learning under Mixture of Distributions
74. ICML 2023Perturbation Analysis of Neural Collapse
75. ICML 2023Phase Transitions in the Detection of Correlated Databases
76. ICML 2023Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models
77. ICML 2023Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice
78. ICML 2023Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality
79. ICML 2023Robust Explanation for Free or At the Cost of Faithfulness
80. ICML 2023Statistical Foundations of Prior-Data Fitted Networks
81. ICML 2023The Computational Complexity of Concise Hypersphere Classification
82. ICML 2023The Edge of Orthogonality: A Simple View of What Makes BYOL Tick
83. ICML 2023The multimarginal optimal transport formulation of adversarial multiclass classification
84. ICML 2023The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
85. ICML 2023The Power of Uniform Sampling for k-Median
86. ICML 2023The Test of Tests: A Framework for Differentially Private Hypothesis Testing
87. ICML 2023The Value of Out-of-Distribution Data
88. ICML 2023The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
89. ICML 2023Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables
90. ICML 2023Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts
91. ICML 2023Under-Counted Tensor Completion with Neural Incorporation of Attributes
92. ICML 2023Understanding Oversquashing in GNNs through the Lens of Effective Resistance
93. ICML 2023Understanding the Impact of Adversarial Robustness on Accuracy Disparity
94. ICML 2023Unit Scaling: Out-of-the-Box Low-Precision Training
95. ICML 2023Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
96. ICML 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpainting
97. ICML 2023Variational Mixture of HyperGenerators for Learning Distributions over Functions
98. ICML 2023When Personalization Harms Performance: Reconsidering the Use of Group Attributes in Prediction
99. NeurIPS 2023[Re] Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification
100. NeurIPS 2023[Re] Numerical influence of ReLU'(0) on backpropagation

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。