Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs Paper • 2605.13737 • Published May 13 • 2
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published Aug 26 • 151
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published Jul 21 • 78