Skip to main content
Search

# H2E

1 related articles

Subscribe to updates
  1. arXiv

    Navigation agents stop calling the LLM every step: H2E distills whole sessions into an 8B VLA, lifting success from 35.0% to 44.9%

    Navigation systems usually have a large language model planner call a vision-language-action (VLA) model at every step, paying LLM cost and delay in each episode. H2E converts successful agent sessions into VLA training data: every motion in a session becomes a VLA action under the original task instruction, steps moving away from the goal are masked from the loss, visited states within 1 m of the goal are labeled as stops, and the VLA is updated with low-rank adaptation. On all REVERIE-CE val-unseen episodes, the 8B VLA's success rate rises from 35.0% to 44.9%, while adaptation to geodesic expert labels gives no gain.

You’re all caught up