Mixture of Experts papers, 2023–2026

Key findings

• Mixture of Experts went from 236 papers in 2023 to 326 in 2026, roughly 1.4x in three years.
• NeurIPS publishes the most Mixture of Experts work: 354 papers from 2023 to 2026, 39% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 4 in 2023 to 79 in 2026.
• Among the 5 topics under Optimization and Scaling, it ranks #4 by 2026 paper count; the fastest grower in the group, Scaling Laws, is up 4.1x versus 1.4x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Mixture of Experts papers

132 papers, page 2 of 3

51. ICML 2026Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
52. ICML 2026Less Token, More Signal: MoE Expert Pruning via Critical Token Selection
53. ICML 2026LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
54. ICML 2026Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
55. ICML 2026Mean-Shift PCA by Knockoff Mean
56. ICML 2026MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
57. ICML 2026MESA: Improving MoE Safety Alignment via Decentralized Expertise
58. ICML 2026MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
59. ICML 2026Mining Tensor/Neuron-Level Sparsity to Maximize Mixture-of-Experts Potential in Post-Training and Inference
60. ICML 2026Mixing Expertise with Confidence: A Mixture of Experts Framework for Robust Multi-Modal Continual Learning
61. ICML 2026Mixture of Concept Bottleneck Experts
62. ICML 2026Mixture of Horizons in Action Chunking
63. ICML 2026Mixtures of geodesic factor analyzers on Riemannian homogeneous spaces
64. ICML 2026MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework
65. ICML 2026MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from Histology
66. ICML 2026MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models
67. ICML 2026MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts
68. ICML 2026Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism
69. ICML 2026Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
70. ICML 2026NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding
71. ICML 2026OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild
72. ICML 2026OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
73. ICML 2026Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
74. ICML 2026PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
75. ICML 2026Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing
76. ICML 2026Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
77. ICML 2026Prism-MoE: Efficient Dense-to-MoE Conversion for Visual Autoregressive Generation
78. ICML 2026ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
79. ICML 2026PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
80. ICML 2026RaGEP: Rank-aware Geometric Expert Pruning for Mixture-of-Experts Language Models
81. ICML 2026RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing
82. ICML 2026Regret Minimization With a Crowd of Awakening Experts
83. ICML 2026ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference
84. ICML 2026RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
85. ICML 2026Rethinking Convergence in MoE Training: The Role of Routing Sparsity
86. ICML 2026Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate
87. ICML 2026Rethinking LLM Ensembling from the Perspective of Mixture Models
88. ICML 2026Rethinking Sparse Mixture of Experts from a Unified Perspective
89. ICML 2026Revisiting Efficiency–Accuracy Scaling in Mixture-of-Experts Architectures
90. ICML 2026Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert Models
91. ICML 2026Robustness of Mixtures of Experts to Feature Noise
92. ICML 2026RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
93. ICML 2026RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
94. ICML 2026SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
95. ICML 2026Sampling and Identity-Testing Without Approximate Tensorization of Entropy
96. ICML 2026ScaleMoE: Mixture-of-Experts for Scalable Continuous Control in Actor-Critic Reinforcement Learning
97. ICML 2026Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts
98. ICML 2026SCHUR-A*: Layer-wise Optimal Expert Pruning for MoEs via Schur-Complement Guided A* Search
99. ICML 2026SD-MoE: Spectral Decomposition for Effective Expert Specialization
100. ICML 2026SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement

FAQ

How many Mixture of Experts papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

904 in total: 236 in 2023, 119 in 2024, 223 in 2025, 326 in 2026.

How many Mixture of Experts papers are at NeurIPS 2026?

NeurIPS 2026 has 75 Mixture of Experts papers, versus 86 the year before.

How many Mixture of Experts papers are at ICLR 2026?

ICLR 2026 has 73 Mixture of Experts papers, versus 59 the year before.

How many Mixture of Experts papers are at ICML 2026?

ICML 2026 has 132 Mixture of Experts papers, versus 57 the year before.

How many Mixture of Experts papers are at CVPR 2026?

CVPR 2026 has 46 Mixture of Experts papers, versus 21 the year before.

Which conference publishes the most Mixture of Experts papers?

NeurIPS, with 354 papers from 2023 to 2026.