LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

Documenti analoghi

• Localizing Task Information for Improved Model Merging and Compression
  di: Wang, Ke, et al.
  Pubblicazione: (2024)
• Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning
  di: Giraldo, Juan Garcia, et al.
  Pubblicazione: (2025)
• Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
  di: Dimitriadis, Nikolaos, et al.
  Pubblicazione: (2024)
• Backdoor Unlearning by Linear Task Decomposition
  di: Abdelraheem, Amel, et al.
  Pubblicazione: (2025)
• MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
  di: Wang, Ke, et al.
  Pubblicazione: (2025)