Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model Paper • 2607.24904 • Published 8 days ago • 32
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published 14 days ago • 76
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe Paper • 2607.03451 • Published Jul 3 • 34
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents Paper • 2605.25624 • Published May 25 • 35