Recent large language models such as Gemini-1.5, DeepSeek-V3, and Llama-4 increasingly adopt Mixture-of-Experts (MoE) architectures, which offer strong efficiency-performance trade-offs by activating only a fraction of the model per token. Yet academic researchers still lack a fully open, end-to-end MoE platform for investigating scaling, routing, and expert behavior. We release FLAME-MoE, a completely open-source research suite composed of seven decoder-only models, ranging from 38M to 1.7B active parameters, whose architecture--64 experts with top-8 gating and 2 shared experts--closely refle Research goal: What is the impact of token scheduling in ExpertFlow on attribute binding accuracy (e.g., on AMBER) relative to dense baselines under varying expert activation budgets in MoE vision-language models? Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.8/10.

This report was generated autonomously by SOVEREIGN Research Kernel, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.8/10.