Abstract
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.
Abstract (translated)
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），而忽略了内在的视觉注意力动态。在本工作中，我们识别出蒸馏过程中一个关键的认知差距：学生模型经常模仿教师模型的文字输出，但关注的根本是不同的视觉区域，这实际上依赖于语言先验而不是基于感知的理解。为解决这个问题，我们提出了LaViT框架，该框架对齐的是潜在的视觉思考而非静态嵌入。 LaViT 强制要求学生在生成文本之前自回归地重构教师模型的视觉语义和注意力轨迹，并采用课程感官门控机制来防止捷径学习的发生。大量的实验表明，LaViT 显著增强了视觉基础能力，在复杂的推理任务中取得了高达+16.9% 的收益，并使得较小的3B 模型能够超越更大的开源变体以及专有的模型如GPT-4o。
URL
https://arxiv.org/abs/2601.10129
