DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks
Paper • 2603.01697 • Published • 2
Gökdeniz Gülmez PRO
Goekdeniz-Guelmez
AI & ML interests
Transformers / NLP / Multimodal / Realtime M2M / J.O.S.I.E.-Home
Recent Activity
liked a Space about 14 hours ago
mrfakename/yue2-3b liked a model about 14 hours ago
Agnes-AI/Agnes-3.0-Flash updated a dataset 1 day ago
Goekdeniz-Guelmez/JOSIE-Zero-4-GRPO-Outputs-105Organizations
submitted a
paper to Daily Papers 7 months ago
authored a
paper 7 months ago