Most unified multimodal models treat images and text asymmetrically: a pretrained language model generates text, an attached diffusion head generates images, and outputs that contain both are produced in a fixed order, so the first output cannot adapt to the second. We ask whether both modalities can instead be generat...
Jia-Han Li, Huang-Yuan Su, Sheng-Bang Tong et al.· 0 citations
Representation alignment improves and accelerates diffusion training by encouraging intermediate features to match a pretrained visual encoder. However, standard alignment matches pretrained representations without distinguishing what information may be more useful for generation. We introduce local appearance purifica...
Yingheng Wang, Yao Li, Ya-Qin Wu et al.· 0 citations
Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields and AR specialising in discrete tokens. Recent work seeks to combine the advantages of the two models, and each hybrid fixes its decoding schedule by design. In this paper...
Unified Latent Diffusion Reasoner improves multimodal reasoning by weaving it into a single thread, where the model predicts successive thoughts in a common representation space.