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

326 papers, page 3 of 7

101. ICLR 2026RLAP-CLIP: Continual Multimodal Learning with Prototype Adaptation and Difficulty-Aware Routing
102. ICLR 2026Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
103. ICLR 2026Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
104. ICLR 2026SafeMoE: Safe Fine-Tuning for MoE LLMs by Aligning Harmful Input Routing
105. ICLR 2026Sem-MoE: Semantic-aware Model-Data Collaborative Scheduling for Efficient MoE Inference
106. ICLR 2026SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
107. ICLR 2026SNaX: sparse narrow accelerated mixture of experts
108. ICLR 2026Steering MoE LLMs via Expert (De)Activation
109. ICLR 2026StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning
110. ICLR 2026Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoders
111. ICLR 2026TD-MoE: Tensor Decomposition for MoE Models
112. ICLR 2026Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
113. ICLR 2026Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models
114. ICLR 2026Transformers Learn Latent Mixture Models In-Context via Mirror Descent
115. ICLR 2026Understanding Routing Mechanism in Mixture-of-Experts Language Models
116. ICLR 2026Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel
117. ICLR 2026UNITE: Universal kNowledge Integration from Task-specific Experts
118. ICLR 2026Unveiling Super Experts in Mixture-of-Experts Large Language Models
119. ICLR 2026Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
120. ICML 2026$\phi$-Balancing for Mixture-of-Experts Training
121. ICML 2026$L^3$: Large Lookup Layers
122. ICML 2026ACO-MoE-LoRA: Evolving-while-Training for Adapting Segment Anything Model 2 to Specialized Domains
123. ICML 2026Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
124. ICML 2026Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
125. ICML 2026Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts
126. ICML 2026Breaking the Echo Chamber: A Dynamic Ensemble Pruning Perspective on MoE
127. ICML 2026Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQA
128. ICML 2026Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization
129. ICML 2026Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE
130. ICML 2026cMoLLM at Scale: Horizontal Scaling Laws for Convolutionally-Gated Mixture-of-LLMs
131. ICML 2026CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning
132. ICML 2026Complexity Bounds for Dirichlet Process Slice Samplers
133. ICML 2026Compositional Generative Modeling from Decentralized Data
134. ICML 2026Conservation Laws for Modern Neural Architectures
135. ICML 2026Continual Model Routing in Evolving Model Hubs
136. ICML 2026CoPE: Continual Probe-guided Expansion for Large Vision-Language Models
137. ICML 2026DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
138. ICML 2026DC-LA: Difference-of-Convex Langevin Algorithm
139. ICML 2026Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
140. ICML 2026Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge
141. ICML 2026Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
142. ICML 2026Discriminative Mixture-of-Experts on Graphs with Reliable Expert Fusion
143. ICML 2026Don't Reinvent the Wheel, Just Realign the Spokes: Resource-Efficient Federated Fine-Tuning via Rank-Wise Expert Assembly
144. ICML 2026DOT-MoE: Differentiable Optimal Transport for MoEfication
145. ICML 2026DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object Detection
146. ICML 2026DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
147. ICML 2026Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting
148. ICML 2026EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference
149. ICML 2026ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots
150. ICML 2026ECO: Quantized Training without Full-Precision Master Weights

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.