CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic

arXiv:2605.18610v1 Announce Type: cross Abstract: Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-scale training data inevitably raises concerns about privacy, copyright, and undesirable content, creating a strong need for machine unlearning. While existing studies mainly focus on single-shot unlearning, practical VLM deployment often involves sequential removal requ