Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering 事件

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering arXiv:2606.01911v1 Announce Type: new Abstract: Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong overall image generation ability, they still underperform on text rendering with blur strokes and disrupt letter shapes. In this work, we trace this limitation to the visual tokenizer, which struggles to recon