1
TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
提出TVI-CoT方法,让多模态大模型在推理时交错利用文本与视觉特征,突破纯文本CoT的视觉信息缺失瓶颈。
arXiv:2606.08464v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has proven effective for enhancing problem-solving in large language …