Skip to main content
Search

# VLA-Δ

1 related articles

Subscribe to updates
  1. arXiv

    Robot policies stop replaying memorized actions: VLA-Δ supervises physical state change in pretraining and reaches 98.40% average on LIBERO

    A Zhejiang University OmniAI team introduces VLA-Δ, which treats the physical change between the current and future state as an explicit pretraining target instead of learning only observation-to-action correspondences. Learnable physical state difference queries in the vision-language backbone are shaped by three signals: structured transition slots, dense optical flow, and future-state difference text; downstream fine-tuning and deployment keep only action generation. It reaches 98.40% average success on LIBERO, exceeds compared methods under both Clean and Random on RoboTwin 2.0, and averages 68.0% across real-robot tasks.

You’re all caught up