X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation
arXiv:2610.21450v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chunk before replanning amortizes this cost, reducing model inference from 195 to 42 ms per executed waypoint for our policy. It also moves the states at which the policy is queried away from expert demonstrations, which supervise neither recovery from these states nor termination at the learner's own…