Embodied AI TopConf · ICLR2026

FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise Decoding

ICLR2026 / Vision-Language-Action Models

VLA感知加速/部署
新标签打开 PDF新标签打开 Paper
FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise Decoding figure
在线论文 PDF（可滚动查看）

精读笔记

精读笔记尚未生成。