LensVLM：压缩文本视觉表示的选取性上下文扩展
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
AI总结：
LensVLM通过选择性上下文扩展提升压缩视觉表示的准确性，在4.3倍压缩下表现优异，且在多模态任务中表现更佳。
摘要：
视觉语言模型（VLMs）提供了将文本作为渲染图像处理的可能性，从而绕过将文本分词为长序列的需要。由于VLM图像编码器将固定大小的图像映射到固定数量的视觉标记，变化的渲染分辨率提供了精细的压缩调节器。然而，随着压缩的增加，准确性迅速下降：字符缩小到视觉编码器的有效分辨率以下，使其无法区分。为此，我们提出了LensVLM，一种推理框架和后训练配方，使VLM能够扫描压缩图像，然后通过学习的工具选择性地将相关图像扩展到未压缩形式。基于Qwen3.5-9B-Base，LensVLM在4.3倍有效压缩下保持与全文上限相当的准确性，并在七个文本问答基准上，比基于检索、文本和视觉压缩的基线高出达10.1倍有效压缩。LensVLM还扩展到多模态文档和代码理解任务，随着压缩的增加，其在基线上的准确性提升也相应增加。我们的分析验证了这种方法：训练使视觉压缩对渲染选择具有鲁棒性，并随着压缩的增加，模型越来越依赖扩展内容而不是不可靠的视觉阅读。分析还提供了实用的工具选择指导：文本扩展更适合渲染文本，而高分辨率图像扩展适合原生文档，其布局提示携带任务相关的信息。
英文摘要：
Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of visual tokens, varying rendering resolution provides a fine-grained compression knob. However, accuracy deteriorates quickly as compression increases: characters shrink below the vision encoder's effective resolution, making them indistinguishable. To address this, we propose LensVLM, an inference framework and post-training recipe that enables VLMs to scan compressed images, then selectively expand only the relevant images to their uncompressed form via learned tools. Building on Qwen3.5-9B-Base, LensVLM maintains accuracy comparable to the full-text upper bound at 4.3$\times$ effective compression and outperforms retrieval-based, text- and visual-compression baselines up to 10.1$\times$ effective compression across seven text QA benchmarks. LensVLM also generalizes to multimodal document and code understanding tasks, with the accuracy gain over baselines growing as compression increases. Our analysis validates this approach: training makes visual compression robust to rendering choices, and as compression grows the model increasingly relies on expanded content rather than unreliable visual reading. The analysis also yields practical tool-choice guidance: text expansion is preferable for rendered text, while high-resolution image expansion suits native documents whose layout cues carry task-relevant information.
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。
