发表机构
University of South Florida（南佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出语义序列化感知接口，将视觉信息转为文本供小语言模型问答，在机器人基准上优于同规模零样本VLM，且优势随模型缩小而增强。
AI 中文摘要
端到端视觉语言模型（VLM）将视觉能力与语言模型的规模绑定在一起：随着语言模型缩小，感知和推理能力会同时下降。我们研究了一种具身场景问答（QA）接口，其中视觉从不进入语言模型。一个冻结的感知堆栈检测物体并测距；一个确定性的语义序列化器将感知状态（包括错误）编译为决策对齐的文本；一个未经修改的纯文本大语言模型（LLM）负责回答。在一个可见范围匹配、遮挡审计的校园机器人基准上，在前瞻性冻结标准下，序列化接口使用每折内域微调的检测器，其性能超过了语言模型规模同为7B的零样本VLM（0.7892对0.7462），在3B规模上差距更大（0.7673对0.6913）。预注册的解耦实验表明，该增益在释义后依然存在，将其归因于决策对齐的计算而非答案字符串泄漏，而新的判断词汇表限制了其适用范围。随着读者规模缩小到1.5B，优势增大，在0.5B时发生逆转，而一个真实值预言机定位了读者能力下限。在匹配的任务监督下，两种接口趋于一致：使用低秩适配（LoRA）微调的VLM超过了零样本系统，但仅与同等监督的文本阅读器持平（0.8441对0.8396，无统计显著差异），且两条路径仍受感知限制。报告的感知参数与VLM视觉塔的参数相当，总计算量并未减少。
英文摘要
End-to-end vision-language models (VLMs) bind visual competence to the scale of their language model: as the language model shrinks, perception and reasoning degrade together. We study an embodied scene question-answering (QA) interface in which vision never enters the language model. A frozen perception stack detects and ranges objects; a deterministic semantic serializer compiles the perceived state, errors included, into decision-aligned text; an unmodified text-only large language model (LLM) answers. On a visible-scope-matched, occlusion-audited campus-robot benchmark, under a prospectively frozen criterion, the serialized interface, using detectors fine-tuned in-domain within each fold, outperforms a zero-shot VLM whose language model has the same 7B scale (0.7892 vs 0.7462), with a larger margin at 3B (0.7673 vs 0.6913). Preregistered decoupling experiments show the gain survives paraphrase, attributing it to decision-aligned computation rather than answer-string leakage, while novel judgment vocabularies bound its scope. The advantage grows as the reader shrinks to 1.5B and reverses at 0.5B, and a ground-truth oracle locates the reader-capability floor. Under matched task supervision the interfaces converge: a VLM fine-tuned with low-rank adaptation (LoRA) overtakes the zero-shot system but only ties an equally supervised text reader (0.8441 vs 0.8396, no statistically resolved difference), and both routes remain perception-bound. Reported perception parameters are comparable to those of the VLM's vision tower, and total compute is not smaller.
Comments12 pages, 2 figures. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
