BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset Paper • 2505.09568 • Published 23 days ago • 90
view article Article OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve By codelion • 17 days ago • 19
RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale Paper • 2505.03005 • Published May 5 • 31
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