Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models 文章

ArXiv CS.CV2026-06-03NEWSen作者: Xinpeng Dong, Min Zhang, Kairong Han, Xu Tan, Fei Wu, Kun Kuang
查看原文 →
关系图谱

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models · 相关技术

相关技术

connector-based paradigmMultimodal Large Language Models (MLLMs)