When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

Documenti analoghi

• Interpretable Debiasing of Vision-Language Models for Social Fairness
  di: An, Na Min, et al.
  Pubblicazione: (2026)
• Safety Alignment for Vision Language Models
  di: Liu, Zhendong, et al.
  Pubblicazione: (2024)
• When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
  di: Yan, Yuping, et al.
  Pubblicazione: (2025)
• Seeing the Abstract: Translating the Abstract Language for Vision Language Models
  di: Talon, Davide, et al.
  Pubblicazione: (2025)
• A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
  di: Jung, Hoin, et al.
  Pubblicazione: (2024)