Video Large Language Models (Video LLMs) have shown remarkable progress in understanding and reasoning about visual content, particularly in tasks involving text recognition and text-based visual question answering (Text VQA). However, deploying Text VQA on wearable devices faces a fundamental tension: text recognition requires high-resolution video, but streaming high-quality video drains battery and causes thermal throttling. Moreover, existing models struggle to maintain coherent temporal context when processing text across multiple frames in real-time streams. We observe that text recognition and visual reasoning have asymmetric resolution requirements - OCR needs fine detail while scene understanding tolerates coarse features. We exploit this asymmetry with a hybrid architecture that performs selective high-resolution OCR on-device while streaming low-resolution video for visual context. On a benchmark of text-based VQA samples across five task categories, our system achieves 72% accuracy at 0.49x the power consumption of full-resolution streaming, enabling sustained VQA sessions on resource-constrained wearables without sacrificing text understanding quality.

翻译：视频大语言模型（Video LLMs）在视觉内容理解与推理方面取得了显著进展，尤其在涉及文本识别和基于文本的视觉问答（Text VQA）任务中。然而，在可穿戴设备上部署Text VQA面临一个根本性矛盾：文本识别需要高分辨率视频，但传输高质量视频会快速消耗电量并引发热降频。此外，现有模型在处理实时视频流中跨多帧的文本时，难以保持连贯的时间上下文。我们观察到文本识别与视觉推理对分辨率的要求具有不对称性——光学字符识别需要精细细节，而场景理解可容忍粗糙特征。基于此，我们提出一种混合架构，在设备端执行选择性高分辨率OCR的同时，传输低分辨率视频以提供视觉上下文。在涵盖五个任务类别的基于文本VQA样本基准测试中，该系统以全分辨率视频流0.49倍的功耗实现了72%的准确率，使得在资源受限的可穿戴设备上能够持续进行VQA会话，且不牺牲文本理解质量。