Semantic-Enriched Latent Visual Reasoning 事件

Semantic-Enriched Latent Visual Reasoning arXiv:2605.19342v2 Announce Type: replace Abstract: Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent representations that lack sufficient semantic richness, limiting their ability to support diverse region-level reasoning tasks. In this work, we introduce Semantic-Enriched La