SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding

Documenti analoghi

• SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
  di: Li, Zhaoxu, et al.
  Pubblicazione: (2025)
• Adversarial Prompt Injection Attack on Multimodal Large Language Models
  di: Ding, Meiwen, et al.
  Pubblicazione: (2026)
• Delve into Visual Contrastive Decoding for Hallucination Mitigation of Large Vision-Language Models
  di: Lee, Yi-Lun, et al.
  Pubblicazione: (2024)
• Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
  di: Xia, Song, et al.
  Pubblicazione: (2024)
• Feature-Space Smoothing: Certified Robustness of Deep Representations
  di: Xia, Song, et al.
  Pubblicazione: (2026)