DialogueVPR：迈向对话式视觉地点识别
DialogueVPR: Towards Conversational Visual Place Recognition
把语言引导的地理定位从静态单样本检索改写为多轮对话式推理，其 DQ-pilot 提问器与 PRG 奖励可直接迁移到任何需要主动消解文本歧义的跨模态检索/定位任务（如文本检索行人、指令式导航）。
原文依据 most methods still rely on a static, one-shot retrieval paradigm, which fails to handle the ambiguity and incompleteness
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论受人类交流空间信息方式的启发，语言引导的地理定位因其直观性与实用价值而受到广泛关注。尽管取得了这些进展，大多数方法仍依赖静态的单样本检索范式，无法应对真实世界自然语言描述中固有的歧义性与不完整性。我们提出向推理式检索的范式转变，并引入对话式地点识别（DlgPR），将定位建模为一个交互式、对话驱动的推理过程。为支持这一新任务，我们提出了 DlgQuest-Cities，这是首个面向地点识别的大规模对话式基准，以及一个统一的推理框架，将跨模态多层级检索器与智能提问器 DQ-pilot 相结合。DQ-pilot 采用课程式训练：先在精心构建的 DQ-cities-20k 子集上进行监督微调，再通过 GRPO 在更难的 DQ-cities-10k 划分上进行强化学习精炼。两个与任务对齐的指标引导学习：用于课程采样的判别难度指数（DDI），以及直接衡量由提问所带来的检索提升的位置检索增益（PRG）奖励。实验表明，这种基于推理的方法显著优于基线。代码将在论文录用后公开。
英文原文摘要 1319 字符
Inspired by how humans communicate spatial information, language-guided geo-localization has gained significant traction for its intuitive and practical value. Despite this progress, most methods still rely on a static, one-shot retrieval paradigm, which fails to handle the ambiguity and incompleteness inherent in real-world natural language descriptions. We propose a paradigm shift to reasoning retrieval and introduce Dialogue Place Recognition (DlgPR), which casts localization as an interactive, dialogue-driven reasoning process. To support this new task, we present DlgQuest-Cities, the first large-scale dialogue-based benchmark for place recognition, and a unified reasoning framework that couples a cross-modal multi-level retriever with an intelligent questioner, DQ-pilot. DQ-pilot is trained in a curriculum: supervised fine-tuning on a curated DQ-cities-20k subset followed by reinforcement refinement on a harder DQ-cities-10k split via GRPO. Two task-aligned metrics guide learning: a Discriminative Difficulty Index (DDI) for curriculum sampling and a Positional Retrieval Gain (PRG) reward that directly measures retrieval improvement induced by a question. Experiments show this reasoning-based approach significantly outperforms baselines. The code will be made publicly available upon acceptance.