2 papers
cs.LG2025
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update
Qing Li, Jiahui Geng, Zongxiong Chen +3
Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large l…
cs.LG2024
Enhance Hyperbolic Representation Learning via Second-order Pooling
Kun Song, Ruben Solozabal, Li hao +5
Hyperbolic representation learning is well known for its ability to capture hierarchical information. However, the distance between samples from different levels of hierarchical cl…