MiniCPM-V 4.7 Collection A new chapter in on-device multimodal Al. • 13 items • Updated 1 day ago • 46
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? Paper • 2605.08985 • Published May 9 • 24
Running on Zero Agents 11 Iris-3B Turbo ⚡ 11 4-step pixel-space text-to-image, distilled from Iris-3B
Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts Paper • 2610.01153 • Published 13 days ago • 24