Open-sourced models of our paper "Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance"
Rhodes Team @ TeleAI
community
AI & ML interests
Foundation Models
Models in "Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach". Credits to Rhodes Team @ TeleAI.
-
rhodes-team-teleai/pi05_TACO_robotwin2_finetuned
4B • Updated • 6 -
rhodes-team-teleai/openvla_TACO_libero10_finetuned
Image-Text-to-Text • 8B • Updated • 2 -
rhodes-team-teleai/pi05_TACO_libero_finetuned
Robotics • 4B • Updated • 9 -
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Paper • 2512.02834 • Published • 42
Open-sourced models of our paper "Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance"
Models in "Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach". Credits to Rhodes Team @ TeleAI.
-
rhodes-team-teleai/pi05_TACO_robotwin2_finetuned
4B • Updated • 6 -
rhodes-team-teleai/openvla_TACO_libero10_finetuned
Image-Text-to-Text • 8B • Updated • 2 -
rhodes-team-teleai/pi05_TACO_libero_finetuned
Robotics • 4B • Updated • 9 -
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Paper • 2512.02834 • Published • 42