Pinned
🚀 Excited to share that our paper Fast-ThinkAct has been accepted to #CVPR2026! 🎉
Efficient Vision-Language-Action reasoning via verbalizable latent planning — enabling embodied agents to think fast internally without lengthy textual reasoning.
⚡ Achieves 9.3× faster
🤖 How can embodied agents think fast—like humans do internally—without lengthy textual reasoning, and still act effectively?
🚀 Introducing Fast-ThinkAct: compact, efficient, verbalizable latent reasoning for Vision-Language-Action models.
Fast think, fast act. 🧠⚡🤲
