Hugging Face Papers ↗ · 2026-11-14
LogT: Logically Think with Images for Visual Search
媒体报道 Hugging Face Papers 原文语言:中文
原文摘录
论文摘要(作者报告,未经本站复测):Thinking with images empowers vision-language models (VLMs) to use an external Zoom-in tool for fine-grained visual search. Recent works employ supervised fine-tuning (SFT) and reinforcement learning (RL) with tool-specific designs to enable such capabilities. However, achieving logical reasoning alongside accurate and efficient tool use remains a significant challenge.
以下是来源提供的简短摘录,完整内容请查看原文。