Can VLMs Actually See and Read? A Survey on Modality Collapse in Vision-Language Models

摘要

Vision-language models (VLMs) integrate textual and visual information, enabling the model to process visual inputs and leverage visual information to generate predictions. Such models are demanding for tasks such as visual question answering, image captioning, and visual grounding. However, some recent work found that VLMs often rely heavily on textual information, ignoring visual information, but are still able to achieve competitive performance in vision-language (VL) tasks. This survey reviews modality collapse analysis work to provide insights into the reason for this unintended behavior. It also reviews probing studies for fine-grained vision-language understanding, presenting current findings on information encoded in VL representations and highlighting potential directions for future research.