RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale Paper • 2505.03005 • Published 2 days ago • 22
MoshiVis v0.1 Collection MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 8 items • Updated Mar 21 • 22