Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation 事件

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation arXiv:2605.18740v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM answers fine-grained questions more accurately when conditioned on evidence-centered crops than on the corresponding fu