Advances in RL Fine-Tuning for Vision-Language-Action Models

FORCE introduces a 3-stage framework to stabilize reinforcement fine-tuning for Vision-Language-Action (VLA) models, addressing sample inefficiency and catastrophic unlearning issues in RL-based fine-tuning.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. UpdateJun 24, 2026, 04:23 PM 84%

   FORCE framework introduced to stabilize and improve RL fine-tuning for Vision-Language-Action models

   FORCE introduces a 3-stage framework to stabilize reinforcement fine-tuning for Vision-Language-Action (VLA) models, addressing sample inefficiency and catastrophic unlearning issues in RL-based fine-tuning.

   Read the full story →