Author name: Bowen Zheng, Weijian Luo, Guang Yang, Colin Zhang, Tianyang Hu

arXiv:2605.06137v1 Announce Type: cross
Abstract: In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction a…

arXiv:2605.06207v1 Announce Type: cross
Abstract: Most discrete visual tokenizers rely on a default design: every position in the sequence shares the same codebook. Researchers try to scale the codebook size $K$ to get better reconstruction performanc…