X-Edit: Exact, Explicit, and Explainable Null-Space Editing for Medical Vision Transformers 事件

X-Edit: Exact, Explicit, and Explainable Null-Space Editing for Medical Vision Transformers arXiv:2605.24932v1 Announce Type: new Abstract: Pre-trained Vision Transformers (ViTs) are increasingly deployed for medical image classification. However, correcting their inevitable failure cases in dynamic clinical scenarios poses a critical challenge. Conventional fine-tuning approaches inherently suffer from catastrophic forgetting, severely degrading previously acquired diagnostic capabilities. Suc