The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Documenti analoghi

• Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
  di: Chatzoudis, Gerasimos, et al.
  Pubblicazione: (2025)
• Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
  di: Gao, Yunhe, et al.
  Pubblicazione: (2023)
• Implicit In-context Learning
  di: Li, Zhuowei, et al.
  Pubblicazione: (2024)
• BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
  di: Wang, Yibin, et al.
  Pubblicazione: (2024)
• TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
  di: Zhang, Tunyu, et al.
  Pubblicazione: (2025)