ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs

Recommended citation: H. U. K. Shinwari and M. Usama (equal contribution), "ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs," IEEE Transactions on Artificial Intelligence, 2025. doi: 10.1109/TAI.2025.3605569.
Paper