Tom Saliencro
@tom-saliencro · 1 works
Recent posts by Tom Saliencro
- Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA - Mixture-of-Experts (MoE) variants of Low-Rank Adaptation (LoRA) route every token to a fixed number of experts $k$. Tokens differ in how uncertain the model is about them, so a single k over-spends… · Paper · arxiv.org
Topics Tom Saliencro posts about
- LoRA on Instagram - 1 post · Best LoRA creators
- MoE on Instagram - 1 post · Best MoE creators