AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization

Ähnliche Einträge

• Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
  von: Wang, Yubo, et al.
  Veröffentlicht: (2024)
• Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining
  von: Liu, Chenxi, et al.
  Veröffentlicht: (2025)
• Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptation
  von: Ji, Yuheng, et al.
  Veröffentlicht: (2024)
• DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model
  von: Tao, Zhou, et al.
  Veröffentlicht: (2025)
• B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions
  von: Zhang, Hao, et al.
  Veröffentlicht: (2024)