L2R improves MoE performance by routing in a low-rank space with Lipschitz-controlled saturated inner-product scoring and multi-anchor mechanisms.
Including such tasks at 10B tokens can introduce noise that obscures routing-induced differences
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts
L2R improves MoE performance by routing in a low-rank space with Lipschitz-controlled saturated inner-product scoring and multi-anchor mechanisms.