AI RESEARCH
Unified Pix Token And Word Token Generative Language Model
arXiv CS.CV
•
ArXi:2605.14028v1 Announce Type: new Since the emergence of Vision Transformer (ViT), it has been widely used in generative language model and generative visual model. Especially in the current state-of-art open source multimodal models, ViT obtained by CLIP or SigLIP method serves as the vision encoder backbone to help them acquire visual understanding capabilities. But this method leads to limitations in visual understanding for details, such as difficulty in recognizing small text or numbers in images.