Can I read Fast-in-Slow: Unified VLA Model on EtoBox?

Fast-in-Slow: Unified VLA Model by zboyangc is a document available to read on EtoBox.

What is Fast-in-Slow: Unified VLA Model about?

The document presents Fast-in-Slow (FiS), a unified dual-system vision-language-action model that integrates a fast execution module (System 1) within a pretrained vision-language model (System 2) to enhance robotic manipulation efficiency. By partially sharing parameters and employing a dual-aware co-training strategy, FiS achieves high-frequency execution while maintaining robust reasoning capabilities, outperforming existing methods in both simulation and real-world tasks. This innovative approach allows

Author

zboyangc

Language

EN