LEV: Thinking Fast and Deep with Looped Decision Models Paper • 2610.20951 • Published 8 days ago • 607
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published 22 days ago • 98
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published 22 days ago • 268