Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?

Documenti analoghi

• How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions
  di: An, Na Min, et al.
  Pubblicazione: (2025)
• I0T: Embedding Standardization Method Towards Zero Modality Gap
  di: An, Na Min, et al.
  Pubblicazione: (2024)
• Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions
  di: Kang, Wan Ju, et al.
  Pubblicazione: (2025)
• Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding
  di: An, Na Min, et al.
  Pubblicazione: (2025)
• Interpretable Debiasing of Vision-Language Models for Social Fairness
  di: An, Na Min, et al.
  Pubblicazione: (2026)