2 papers
cs.CV2025
When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs
Aobotao Dai, Xinyu Ma, Lei Chen +2
Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual in…
cs.CV2025
Rethinking Knowledge in Distillation: An In-context Sample Retrieval Perspective
Jinjing Zhu, Songze Li, Lin Wang
Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationsh…