4 papers
LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
Hadi Askari, Shivanshu Gupta, Fei Wang +2
Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks, yet exhibit substantial variability in the various layers' training quality with re…
VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap
Qin Liu, Fei Wang, Chaowei Xiao +1
The emergence of vision language models (VLMs) comes with increased safety concerns, as the incorporation of multiple modalities heightens vulnerability to attacks. Although VLMs c…
Unraveling Indirect In-Context Learning Using Influence Functions
Hadi Askari, Shivanshu Gupta, Terry Tong +3
In this work, we introduce a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection stra…
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
Yingzi Ma, Jiongxiao Wang, Fei Wang +10
Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy c…