Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update

Documenti analoghi

• SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
  di: Li, Qing, et al.
  Pubblicazione: (2025)
• Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings
  di: Abid, Abderrazek, et al.
  Pubblicazione: (2025)
• REMONI: An Autonomous System Integrating Wearables and Multimodal Large Language Models for Enhanced Remote Health Monitoring
  di: Ho, Thanh Cong, et al.
  Pubblicazione: (2025)
• CosmoCLIP: Generalizing Large Vision-Language Models for Astronomical Imaging
  di: Imam, Raza, et al.
  Pubblicazione: (2024)
• Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
  di: Aladawi, Aljalila, et al.
  Pubblicazione: (2026)