When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models

Documenti analoghi

• Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models
  di: Cai, Wei, et al.
  Pubblicazione: (2025)
• A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization
  di: Li, LinFeng, et al.
  Pubblicazione: (2025)
• Visual Attention Reasoning via Hierarchical Search and Self-Verification
  di: Cai, Wei, et al.
  Pubblicazione: (2025)
• TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations
  di: Chen, Xiuyuan, et al.
  Pubblicazione: (2025)
• Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration
  di: He, Yuxiang, et al.
  Pubblicazione: (2025)