LoRASculpt: Harmonious Low-Rank Adaptation for Multimodal Large Language Models

LoRASculpt+ is a framework that improves how multimodal large language models (MLLMs, AI systems that process both text and images) can be adapted to specific tasks while keeping their general knowledge. The method uses sparse LoRA updates (a parameter-efficient technique that only modifies a small set of weights rather than all parameters) with regularization to reduce unnecessary changes during training and prevent the model from forgetting what it already knows.