AIBullisharXiv – CS AI · 8h ago6/10
🧠
BoostLoRA: Growing Effective Rank by Boosting Adapters
BoostLoRA introduces a gradient-boosting framework that enables parameter-efficient fine-tuning adapters to grow their effective rank iteratively, allowing ultra-low-parameter models to match or exceed full fine-tuning performance across mathematical reasoning, code generation, and protein classification tasks. The method merges adapters with zero inference overhead while maintaining minimal per-round parameter costs.