Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed Compute
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- FFN Fusion: Rethinking Sequential Computation in Large Language Models
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
- DeepSeek-V3 Technical Report
- Multi-branch Attentive Transformer
- Training Compute-Optimal Large Language Models
- GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
- Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective
- Soft Merging of Experts with Adaptive Routing
- Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models
- Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
- The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
- From Sparse to Soft Mixtures of Experts
- GLU Variants Improve Transformer
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching
- SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs
- MoEfication: Transformer Feed-forward Layers are Mixtures of Experts
- ST-MoE: Designing Stable and Transferable Sparse Expert Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks