Can Visual Generation Expand What Unified Multimodal Models Know?
Unified multimodal models (UMMs) receive image-generation supervision that exposes them to visual information not fully documented in text. Can learning to generate images expand what pretrained models know? We introduce Knowledge Transfer Probing (KTP), a controlled protocol that supplies new knowledge through image-g...
Wen-Kai Li, Wen-Yi Hong, Zhuo-Yi Yang et al.
· 0 citations