医学图像对齐评估：前沿多模态模型通用视觉推理测试
原标题：Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models
AI 摘要
该研究将医学图像对齐评估作为检验前沿多模态大模型通用视觉推理能力的测试任务，评估了多代MLLM在两种医学图像对齐任务上的表现，并对比了本地微调小模型和任务专用CNN。结果显示，仅几个月前发布的模型泛化能力差、部分场景接近随机水平，而GPT-6在几乎所有测试场景（包括零样本）中准确率超过85%。微调本地模型在训练任务上可匹敌或超越前沿模型，但迁移到未见场景时效果明显下降。
正文节选
Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models Abstract Frontier multimodal large language models (MLLMs) are increasingly positioned as general purpose visual reasoners as part of the quest for artificial general intelligence. A key test of this generality is whether they can perform novel visual judgments that humans can make reliably from visual evidence and task instructions, without task-specific parameter optimisation. We investiga