VLA-TTS: TACO
Collection
Models in "Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach". Credits to Rhodes Team @ TeleAI.
•
4 items
•
Updated
•
2
pi05 finetuned on the dataset mixed over LIBERO-Spatial, LIBERO-Goal, LIBERO-Object and LIBERO-Long, together with our trained CFN.
- Downloads last month
- 24