3 citations · 5 across the 5 of their papers we have counts for
4 papers · 1 filter
SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models
Caoyuan Ma, Tian Gu, Wenpu Liu +11
Existing safety alignment methods for vision-language models usually modify the model behavior globally: once the safety parameters are trained or loaded, they participate in both…
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning
Caoyuan Ma, Wenpu Liu, Weichu Xie +12
Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their language backbones. We propos…
Adapter-Enhanced Semantic Prompting for Continual Learning
Baocai Yin, Ji Zhao, Huajie Jiang +5
Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired…
Enhancing Vectorized Map Perception with Historical Rasterized Maps
Xiaoyu Zhang, Guangwei Liu, Zihao Liu +3
In autonomous driving, there is growing interest in end-to-end online vectorized map perception in bird's-eye-view (BEV) space, with an expectation that it could replace traditiona…