与图像对话以进行反思性视觉思维
Chatting with Images for Introspective Visual Thinking
AI总结：
ViLaVT通过语言引导的特征调节框架，实现多图像区域的联合重编码，提升跨模态对齐与复杂空间推理能力。
摘要：
当前的大型视觉-语言模型（LVLMs）通常依赖于基于单一通路视觉编码的纯文本推理，这常常导致细粒度视觉信息的丢失。最近提出的
英文摘要：
Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking with images'' attempts to alleviate this limitation by manipulating images via external tools or code; however, the resulting visual states are often insufficiently grounded in linguistic semantics, impairing effective cross-modal alignment - particularly when visual semantics or geometric relationships must be reasoned over across distant regions or multiple images. To address these challenges, we propose ''chatting with images'', a new framework that reframes visual manipulation as language-guided feature modulation. Under the guidance of expressive language prompts, the model dynamically performs joint re-encoding over multiple image regions, enabling tighter coupling between linguistic reasoning and visual state updates. We instantiate this paradigm in ViLaVT, a novel LVLM equipped with a dynamic vision encoder explicitly designed for such interactive visual reasoning, and trained it with a two-stage curriculum combining supervised fine-tuning and reinforcement learning to promote effective reasoning behaviors. Extensive experiments across eight benchmarks demonstrate that ViLaVT achieves strong and consistent improvements, with particularly pronounced gains on complex multi-image and video-based spatial reasoning tasks.
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。
