KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing
KVEraser: 学习操控KV缓存以实现高效的局部上下文擦除
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Meta
AI总结 提出KVEraser方法,通过学习操控KV缓存实现局部上下文擦除,避免全局重计算,在长上下文任务中接近全重算性能且延迟仅增加24%。
Comments Oral at the ICML 2026 Workshop on the Impact of Memorization on Trustworthy Foundation Models; Code available at https://github.com/Graph-COM/KVEraser