<ul><li>Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence.</li><li>Parameter-efficient fine-tuning (PEFT) methods like LoRA have emerged and are becoming a growing research focus.</li><li>A generalization of matrix-based PEFT methods to higher-dimensional parameter spaces is proposed, preserving the structural properties.</li><li>Extensive experiments on computer vision and natural language processing validate the effectiveness and versatility of the approach.</li></ul>

Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations

Discover more