AI RESEARCH
Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
arXiv CS.LG
•
ArXi:2605.18740v1 Announce Type: cross 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 accurately when conditioned on evidence-centered crops than on the corresponding full images, suggesting that many failures stem from difficulty to focus on relevant evidence rather than insufficient local recognition ability.