Forgotten Polygons: Multimodal Large Language Models are Shape-Blind

Documenti analoghi

• What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
  di: Golovanevsky, Michal, et al.
  Pubblicazione: (2024)
• Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
  di: Golovanevsky, Michal, et al.
  Pubblicazione: (2025)
• Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
  di: Rudman, William, et al.
  Pubblicazione: (2026)
• Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models
  di: McLaughlin, Oliver, et al.
  Pubblicazione: (2026)
• Stable Anisotropic Regularization
  di: Rudman, William, et al.
  Pubblicazione: (2023)