F1-VLA

Papers using or citing this model 1

• F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions 87 citations · 2025 · arXiv.org · arXiv

  Executing language-conditioned tasks in dynamic visual environments remains a central challenge in embodied AI. Existing Vision-Language-Action (VLA) models predominantly adopt reactive state-to-action mappings, often leading to...