SyncAI.news, a Varaisys broadcasting
GRAFT: Cross-Backbone LoRA Reuse for Continual Language and Multimodal Learning
HP

Ha Pham Thien Dinh, Ming Liu, Jiesi Guo, Matteo Vergani, Kewen Liao

· 1 min read

ResearcharXiv cs.LG

GRAFT: Cross-Backbone LoRA Reuse for Continual Language and Multimodal Learning

arXiv:2611.18638v1 Announce Type: new Abstract: In continual learning, parameter-efficient fine-tuning enables large language models to acquire new capabilities through lightweight adapters such as LoRA, yet the reuse of pretrained adapters is typically restricted to models sharing the same backbone. This limits the transfer of learned capabilities from language models to multimodal models. We propose GRAFT (Generalist Reuse of Adapters via Feature-space Transfer), a framework for cross-backbone LoRA reuse. GRAFT retrieves the most relevant pretrained LoRA adapter from a modality-aware library and maps it into the target backbone through a learned linear bridge between corresponding source and target feature spaces. We evaluate GRAFT on ten Super-NaturalInstructions text tasks, transferring Qwen2.5 LoRAs to Qwen2.5-VL, and five multimodal tasks, where Qwen2.5-VL LoRAs are directly reused. Compared with randomly initialized LoRA adapters, GRAFT improves performance on most evaluated tasks. These results show that GRAFT provides a simple and effective mechanism for reusing learned capabilities across language and multimodal models in continual learning.

Original source

This story was published by arXiv cs.LG and written by Ha Pham Thien Dinh, Ming Liu, Jiesi Guo, Matteo Vergani, Kewen Liao. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News