AI RESEARCH
Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training
arXiv CS.CV
•
ArXi:2603.25706v1 Announce Type: new Recent unified models have made unprecedented progress in both understanding and generation. However, while most of them accept multi-modal inputs, they typically produce only single-modality outputs. This challenge of producing interleaved content is mainly due to