Cross-LoRA transfers LoRA adapters across heterogeneous LLMs by aligning source and target base-model subspaces with rank-truncated SVD and a Frobenius-optimal linear map, data-free and training-free.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
Cross-LoRA transfers LoRA adapters across heterogeneous LLMs by aligning source and target base-model subspaces with rank-truncated SVD and a Frobenius-optimal linear map, data-free and training-free.