LoMo: Local Modality Substitution for Deeper Vision-Language Fusion 事件

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion arXiv:2605.30265v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its rendered-image counterpart should leave model performance essentially unaffected. In practice, however, such modality substitution induces dram