arXiv (All)
open access
Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models
Modern fine-grained Mixture-of-Experts (MoE) models route each token to a small number of experts and renormalize their router probabilities. We show that this renormalization implicitly calibrates expert output gain to the training top-$k$: reducing $k$ at inference changes not only which experts a
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Prediction-powered Inference by Mixture of Experts#146949
- Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization#1160986
- Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization#1155493
- Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts#471242
- Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models#332492
Record · ID 927851
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive