Decoupled Global-Local Alignment for Improving Compositional Understanding Paper • 2504.16801 • Published 1 day ago • 14
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing Paper • 2504.02826 • Published 21 days ago • 67
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm Paper • 2502.12513 • Published Feb 18 • 16