Attention, Please! PixelSHAP Reveals What Vision-Language Models Actually Focus On

Documenti analoghi

• Beyond the Beep: Scalable Collision Anticipation and Real-Time Explainability with BADAS-2.0
  di: Goldshmidt, Roni, et al.
  Pubblicazione: (2026)
• TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation
  di: Goldshmidt, Roni, et al.
  Pubblicazione: (2024)
• From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
  di: Shang, Yuying, et al.
  Pubblicazione: (2024)
• Investigating Spatial Attention Bias in Vision-Language Models
  di: Chaudhary, Aryan, et al.
  Pubblicazione: (2025)
• Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
  di: Li, Bin, et al.
  Pubblicazione: (2025)