SheepNav
新上线今天0 投票

MedExpMem: Adapting Experience Memory for Differential Diagnosis

arXiv:2605.22872v1 Announce Type: new Abstract: Experienced physicians develop diagnostic expertise through clinical practice, acquiring not only disease knowledge but also the ability to differentiate confusable conditions. Current medical vision-language models (VLMs) lack this capability -- their parameters encode static knowledge that does not evolve across diagnostic encounters. We propose MedExpMem, an experience memory framework enabling VLM-based diagnostic agents to accumulate different

延伸阅读

  1. LLM何时需要推理?熵相变视角下的动态系统解读
  2. Manifold Representation Forgetting:一种基于流形表示遗忘的近似机器反学习新方法
  3. 思维链推理的“捷径”:小语言模型算术任务中的位置复制机制
查看原文