Skip to content
conftrace_
2025 ICML ICML 2025

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Saketh Bachu, Erfan Shayegani, Rohit Lal, Trishna Chakraborty, Arindam Dutta, Chengyu Song, Yue Dong, Nael B. Abu-Ghazaleh, Amit Roy-Chowdhury

Topics

Reinforcement Learning > Methods > Policy Learning Artificial Intelligence > Core AI > Large Language Models Deep Learning > Learning Types > Multimodal Learning

Keywords

early exit vision-language model harmful information clipped-proximal policy optimization image encoder layers layer-wise ppo
Download PDF