Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critical Perception Gap in distillation: student models frequently mimic a teacher's textual output while attending to fundamentally divergent visual regions, effectively relying on language priors rather than grounded perception. To bridge this, we propose LaViT, a framework that aligns latent visual thoughts rather than static embeddings. LaViT compels the student to autoregressively reconstruct the teacher's visual semantics and attention trajectories prior to text generation, employing a curriculum sensory gating mechanism to prevent shortcut learning. Extensive experiments show that LaViT significantly enhances visual grounding, achieving up to +16.9% gains on complex reasoning tasks and enabling a compact 3B model to outperform larger open-source variants and proprietary models like GPT-4o.

翻译：当前的多模态潜在推理通常依赖于外部监督（例如辅助图像），而忽视了内在的视觉注意力动态。在本研究中，我们识别了知识蒸馏中存在的一个关键“感知鸿沟”：学生模型经常模仿教师的文本输出，却关注于根本不同的视觉区域，这实质上依赖于语言先验而非基于感知的推理。为弥合此鸿沟，我们提出了LaViT框架，该框架旨在对齐潜在的视觉思维，而非静态嵌入。LaViT强制学生在文本生成之前，自回归地重构教师的视觉语义和注意力轨迹，并采用课程式感官门控机制以防止捷径学习。大量实验表明，LaViT显著增强了视觉基础，在复杂推理任务上实现了高达+16.9%的性能提升，并使一个紧凑的30亿参数模型能够超越更大的开源变体及GPT-4o等专有模型。