Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models
Yejin Kim, Dongjun Hwang, Sungmin Cha +1
Large Vision-Language Models (LVLMs) are widely adopted for their strong multimodal capabilities, yet they raise serious concerns such as privacy leakage and harmful content genera…
cs.LG2025
Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
Sungjun Cho, Dasol Hwang, Frederic Sala +3
Current unlearning metrics for generative models evaluate success based on reference responses or classifier outputs rather than assessing the core objective: whether the unlearned…
cs.LG2025
Why Alignment Must Precede Distillation: A Minimal Working Explanation
Sungmin Cha, Kyunghyun Cho
For efficiency, preference alignment is often performed on compact, knowledge-distilled (KD) models. We argue this common practice introduces a significant limitation by overlookin…