Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models

Documenti analoghi

• HRVDA: High-Resolution Visual Document Assistant
  di: Liu, Chaohu, et al.
  Pubblicazione: (2024)
• AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization
  di: Liu, Chaohu, et al.
  Pubblicazione: (2025)
• BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
  di: Tang, Jianting, et al.
  Pubblicazione: (2025)
• When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition
  di: Sun, Xiaokun, et al.
  Pubblicazione: (2026)
• Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
  di: Li, Xin, et al.
  Pubblicazione: (2024)