指出你的意图：基于视觉的指令策略
Point What You Mean: Visually Grounded Instruction Policy
AI总结：
本文提出Point-VLA，通过结合视觉提示提升物体指称能力，在复杂场景中实现更精准的视觉 grounding。
摘要：
Vision-Language-Action (VLA) 模型通过结合视觉和语言实现具身控制，但仅依赖文本提示时在复杂或分布外场景中物体指称能力受限。本文引入Point-VLA，一种可插拔策略，通过添加显式视觉提示（如边界框）来解决指称歧义并实现精确物体级 grounding。为高效扩展视觉 grounded 数据集，我们进一步开发了自动数据标注管道，仅需少量人工努力。我们在多样化的现实指称任务上评估Point-VLA，并观察到其在复杂或未见物体场景中比纯文本指令VLA表现更优，具有更强的泛化能力。这些结果表明，Point-VLA通过像素级视觉 grounding 有效解决物体指称歧义，实现更通用的具身控制。
英文摘要：
Vision-Language-Action (VLA) models align vision and language with embodied control, but their object referring ability remains limited when relying solely on text prompt, especially in cluttered or out-of-distribution (OOD) scenes. In this study, we introduce the Point-VLA, a plug-and-play policy that augments language instructions with explicit visual cues (e.g., bounding boxes) to resolve referential ambiguity and enable precise object-level grounding. To efficiently scale visually grounded datasets, we further develop an automatic data annotation pipeline requiring minimal human effort. We evaluate Point-VLA on diverse real-world referring tasks and observe consistently stronger performance than text-only instruction VLAs, particularly in cluttered or unseen-object scenarios, with robust generalization. These results demonstrate that Point-VLA effectively resolves object referring ambiguity through pixel-level visual grounding, achieving more generalizable embodied control.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
