GRAFT Method Enables Cross-Backbone LoRA Reuse for Continual Language and Multimodal Learning
A new arXiv paper introduces GRAFT, a method for reusing LoRA adapters across different backbones in continual learning, letting large language models gain new capabilities via lightweight parameter-efficient fine-tuning for both language and multimodal tasks.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv cs.LG
GRAFT: Cross-Backbone LoRA Reuse for Continual Language and Multimodal Learning