latam-gpt/Wayra-Perplexity-Estimator-55M Text Classification • 55.4M • Updated 29 days ago • 3.06k • • 21
LogitRouter Collection Models of the Paper LogitRouter: a novel Attention variant for reducing Myopic Routing in Mixture of Experts • 9 items • Updated Dec 1, 2025 • 1
LogitRouter Collection Models of the Paper LogitRouter: a novel Attention variant for reducing Myopic Routing in Mixture of Experts • 9 items • Updated Dec 1, 2025 • 1