研究人员推出了一种新颖的持续机器学习遗忘方法CATA，用于视觉语言模型（VLMs）。该方法解决了在保留模型整体性能的同时，顺序删除VLMs中特定数据的挑战。CATA利用冲突规避任务算术将遗忘请求表示为向量，有效管理冲突更新并确保知识被持久删除。 AI
影响 为大型视觉语言模型提供了更强大、更注重隐私的更新。
排序理由 该集群包含一篇描述新机器学习方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
CATA方法实现了视觉语言模型的持续机器学习遗忘
报道来源 [2]
-
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
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, cre…
-
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
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, cre…