← back to paper

Review history

arxiv: 2608.09467 · 2 revisions

RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   109719 ms 12824 in 13180 out 2026-08-15T14:23:11.641035+00:00
2. 2026-08-11 CONDITIONAL MODERATE v1.4.0-daily-deepseek-medium novelty 6.0
   120357 ms 12841 in 14078 out 2026-08-11T17:00:15.433869+00:00