解锁潜在画布：在LLMs中引发和评估符号视觉表达
Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs
AI总结：
本文通过ASCII艺术格式揭示LLMs的潜在视觉能力，提出SVE-ASCII框架，构建ASCIIArt-7K数据集，并展示生成训练如何提升视觉理解，建立文本基视觉智能的基准。
摘要：
当前多模态方法大多将视觉生成视为外部过程，依赖像素渲染或代码执行，忽略了LLMs中潜在的视觉表示能力。本文通过ASCII艺术，一种紧凑高效的文本原生视觉格式，解锁这一潜力。我们引入SVE-ASCII框架，直接在纯文本空间中引发和评估符号视觉表达。为解决系统资源稀缺问题，我们构建了通过新型
英文摘要：
Current multimodal approaches predominantly treat visual generation as an external process, relying on pixel rendering or code execution, thereby overlooking the native visual representation capabilities latent within Large Language Models (LLMs). In this work, we unlock this potential through ASCII art, a compact, efficient, and text-native visual format. We introduce SVE-ASCII, a unified framework designed to elicit and benchmark Symbolic Visual Expression directly within the pure text space. To address the scarcity of systematic resources, we construct ASCIIArt-7K, a high-quality dataset synthesized via a novel "Seed-and-Evolve" pipeline that augments human-curated anchors through in-context stylistic editing. We further implement a unified instruction-tuning strategy that jointly optimizes for both Generation (Text-to-ASCII) and Understanding (ASCII-to-Text). Crucially, our experiments reveal a critical phenomenon regarding task duality: while it is established that perception aids generation, we provide compelling evidence that generative training significantly enhances visual comprehension. This confirms a mutually reinforcing cycle in symbolic visual processing, a relationship previously hypothesized but rarely empirically demonstrated in the visual domain. We release our dataset, the ASCIIArt-Bench benchmark, and the SVE-ASCII model, establishing a robust baseline for native text-based visual intelligence.
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。
