BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity

Documenti analoghi

• Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
  di: Li, Shiwei, et al.
  Pubblicazione: (2025)
• The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
  di: Li, Shiwei, et al.
  Pubblicazione: (2025)
• Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
  di: Li, Shiwei, et al.
  Pubblicazione: (2025)
• BoRA: Bi-dimensional Weight-Decomposed Low-Rank Adaptation
  di: Wang, Qiushi, et al.
  Pubblicazione: (2024)
• Masked Random Noise for Communication Efficient Federated Learning
  di: Li, Shiwei, et al.
  Pubblicazione: (2024)