ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models
Image-to-text (I2T) understanding and text-to-image (T2I) generation are dual tasks in unified multimodal models (UMMs). Reconstructive post-training couples these tasks, but existing reconstruction-based methods remain perception-centric and provide limited supervision for reasoning about…
arXiv - cs.CV (CV)2 min read