Efficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models

Documenti analoghi

• LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
  di: Li, Wenbing, et al.
  Pubblicazione: (2025)
• R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-Task Learning
  di: Liu, Jinda, et al.
  Pubblicazione: (2025)
• FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
  di: Lee, Seanie, et al.
  Pubblicazione: (2025)
• Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
  di: Zhang, Haobo, et al.
  Pubblicazione: (2025)
• SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA
  di: Luo, Minrui, et al.
  Pubblicazione: (2025)