MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models

Documenti analoghi

• RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting
  di: Jiang, Yilei, et al.
  Pubblicazione: (2024)
• HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States
  di: Jiang, Yilei, et al.
  Pubblicazione: (2025)
• QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems
  di: Yang, Yiliu, et al.
  Pubblicazione: (2025)
• Safety Alignment for Vision Language Models
  di: Liu, Zhendong, et al.
  Pubblicazione: (2024)
• ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection
  di: Ma, Ruize, et al.
  Pubblicazione: (2025)