LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning

摘要

Current multimodal latent reasoning often relies on externalsupervision (e.g., auxiliary images), ignoring intrinsic visual attentiondynamics. In this work, we identify a critical Perception Gap in distil-lation: student models frequently mimic a teacher’s textual output whileattending to fundamentally divergent visual regions, effectively relyingon language priors rather than grounded perception. To bridge this, wepropose LaViT, a framework that aligns latent visual thoughts ratherthan static embeddings. LaViT compels the student to autoregressivelyreconstruct the teacher’s visual semantics and attention trajectories priorto text generation, employing a curriculum sensory gating mechanism toprevent shortcut learning. Extensive experiments show that LaViT sig-nificantly enhances visual grounding, achieving up to +16.9% gains oncomplex reasoning tasks and enabling a compact 3B model to rival largermodels on selected evaluated benchmarks.