Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models

Documenti analoghi

• Reducing Hallucinations in Vision-Language Models via Latent Space Steering
  di: Liu, Sheng, et al.
  Pubblicazione: (2024)
• The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
  di: Li, Zhuowei, et al.
  Pubblicazione: (2025)
• SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues
  di: Hinojosa, Carlos, et al.
  Pubblicazione: (2026)
• Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
  di: Dafnis, Konstantinos M., et al.
  Pubblicazione: (2025)
• Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
  di: Lee, Yousung, et al.
  Pubblicazione: (2026)