Author name: Jiayi Chen, Wenxuan Song, Shuai Chen, Jingbo Wang, Zhijun Li, Haoang Li

arXiv:2603.26320v3 Announce Type: replace-cross
Abstract: Vision–Language–Action (VLA) models that encode actions using a discrete tokenization scheme are increasingly adopted for robotic manipulation, but existing decoding paradigms remain fundamen…

arXiv:2603.26320v2 Announce Type: replace-cross
Abstract: Vision–Language–Action (VLA) models that encode actions using a discrete tokenization scheme are increasingly adopted for robotic manipulation, but existing decoding paradigms remain fundamen…

arXiv:2603.26320v1 Announce Type: cross
Abstract: Vision–Language–Action (VLA) models that encode actions using a discrete tokenization scheme are increasingly adopted for robotic manipulation, but existing decoding paradigms remain fundamentally li…