GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models

Documenti analoghi

• ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression
  di: Yao, Kai, et al.
  Pubblicazione: (2024)
• Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
  di: Yao, Kai, et al.
  Pubblicazione: (2024)
• GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection
  di: Yao, Kai, et al.
  Pubblicazione: (2026)
• GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
  di: Huang, Wei, et al.
  Pubblicazione: (2026)
• GradNetOT: Learning Optimal Transport Maps with GradNets
  di: Chaudhari, Shreyas, et al.
  Pubblicazione: (2025)