LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Ähnliche Einträge

• Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
  von: Lee, Yu-Ang, et al.
  Veröffentlicht: (2026)
• Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models
  von: Mahla, Navyansh, et al.
  Veröffentlicht: (2024)
• Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
  von: Liu, Yuhang, et al.
  Veröffentlicht: (2025)
• KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
  von: Azimi, Rambod, et al.
  Veröffentlicht: (2024)
• Parameter-Efficient Fine-Tuning for HAR: Integrating LoRA and QLoRA into Transformer Models
  von: Seregina, Irina, et al.
  Veröffentlicht: (2025)