By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.
arXiv preprint arXiv:2008.03371 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
FRAMP generates client-specific models from compact descriptors in federated learning, trains tailored submodels, and aligns representations to balance personalization with global consistency.
citing papers explorer
-
Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.