#artificial intelligence
Sep 2026
Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation
This work proposes SeekVLN, an evidence-seeking framework that couples semantic progress reasoning with active acquisition of task-relevant observations and introduces Counterfactual Contrastive Policy Optimization (C2PO) for reinforcement fine-tuning.
Zhi-Min Wang, Mei-Yuan Zhu, Duo Wu et al.
· arXiv.org · 0 citations