指向部件：多模态大语言模型中的免训练少样本视觉定位
Pointing at Parts: Training-Free Few-Shot Grounding in Multimodal LLMs
提出一种免训练、即插即用的少样本部件级指向方法，通过融合文本与视觉注意力图以及自监督视觉对应，可提升MLLM在细粒度空间定位任务上的表现，为视觉语言模型的空间理解提供可复用技术。
原文依据 POP fuses textual and visual attention maps with self-supervised visual correspondences from query image and few-shot examples.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论部件级指向对于细粒度交互和推理很重要，然而现有的多模态大语言模型（MLLMs）仍局限于实例级指向。部件级指向面临独特挑战：标注成本高、部件呈长尾分布，且许多部件难以用语言精确指定。我们提出指向部件（POP），一种免训练、即插即用的方法，在少样本设定下应对这些挑战。POP将文本和视觉注意力图与来自查询图像和少样本示例的自监督视觉对应相融合。在三个评估数据集上平均而言，对于具备指向能力的MLLMs——Qwen2.5-VL、Ovis2.5和Molmo，POP在单样本设定下准确率提升高达8.9个百分点，在三样本设定下提升高达16.4个百分点。值得注意的是，即使是不具备指向能力的MLLMs也从所提方法中显著受益。这些结果为MLLMs中的细粒度空间视觉定位建立了一条简单而有效的路径。
英文原文摘要 1019 字符
Part-level pointing is important for fine-grained interaction and reasoning, yet existing Multimodal Large Language Models (MLLMs) remain limited to instance-level pointing. Part-level pointing presents unique challenges: annotation is costly, parts are long-tail distributed, and many are difficult to specify precisely in language. We introduce POinting at Parts (POP), a training-free, plug-and-play approach that addresses these challenges under a few-shot setup. POP fuses textual and visual attention maps with self-supervised visual correspondences from query image and few-shot examples. On average across the three evaluated datasets, POP achieves accuracy gains of up to 8.9 points in the one-shot setting and 16.4 points in the three-shot setting for the pointing-capable MLLMs--Qwen2.5-VL, Ovis2.5, and Molmo. Notably, even MLLMs without pointing capability benefit significantly from the proposed approach. These results establish a simple yet effective path toward fine-grained spatial grounding in MLLMs.