Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models

Documenti analoghi

• Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning
  di: Kim, Yejin, et al.
  Pubblicazione: (2025)
• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
  di: Cha, Sungmin, et al.
  Pubblicazione: (2024)
• NegMerge: Sign-Consensual Weight Merging for Machine Unlearning
  di: Kim, Hyo Seo, et al.
  Pubblicazione: (2024)
• Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
  di: Cha, Sungmin, et al.
  Pubblicazione: (2023)
• Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
  di: Kim, Yongwoo, et al.
  Pubblicazione: (2025)