VIF

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

arXiv:2605.18160v2 Announce Type: replace Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information. The dominant connector-based paradigm projects visual features into textual sequence, enabling unified multimodal alignment and reasoning within a generative architecture. However, our experiments reveal two key limitations: (1) Although visual information...