Kangsan Kim

The paper proposes SELFCI, a complementary self-distillation framework that effectively balances the privacy requirements of Contextual Integrity (CI) with the utility of large language models, outperforming existing methods without external supervision.

The paper introduces LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference agent, achieving significant performance gains on OSWorld.