{"ID":5937931,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T09:41:33.197749305Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03792","arxiv_id":"2607.03792","title":"From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation","abstract":"Vision-and-Language Navigation (VLN) agents may satisfy conventional success criteria while still failing to establish reliable object-level grounding, because current evaluation protocols mainly reward stopping within a 3-meter radius and largely ignore the agent's final orientation and target visibility. We formalize this limitation as the Last-3-Meter Grounding Gap and introduce three instance-centric metrics to quantify proximity precision, target visibility, and final-view grounding. To mitigate this gap, we propose REALM (Region-to-Entity Alignment for Last-3-Meter Navigation), a plug-and-play, architecture-agnostic refinement module that decouples fine-grained target approaching from long-horizon navigation. REALM uses a visibility-aware stopping strategy to reduce premature termination and improve final viewpoint alignment. We further construct REVERIE-AIM, which provides object-instance-level goals and 180K short-horizon training samples for final-stage target approaching. Extensive evaluations across four diverse VLN backbones show that REALM consistently improves proximity precision and visual grounding success, demonstrating its broad applicability.","short_abstract":"Vision-and-Language Navigation (VLN) agents may satisfy conventional success criteria while still failing to establish reliable object-level grounding, because current evaluation protocols mainly reward stopping within a 3-meter radius and largely ignore the agent's final orientation and target visibility. We formalize...","url_abs":"https://arxiv.org/abs/2607.03792","url_pdf":"https://arxiv.org/pdf/2607.03792v1","authors":"[\"Xiangyu Shi\",\"Ruoxi Yang\",\"Wei Tao\",\"Jiwen Zhang\",\"Yanyuan Qiao\",\"Qi Wu\"]","published":"2026-07-04T09:44:57Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\"]","methods":"[]","has_code":false}