2 papers
cs.AI2026
Understanding LoRA Rank Trade-offs in Diffusion Model Fine-Tuning
Iman Khazrak, Narges Nejad, Mostafa M. Rezaee +1
Selecting LoRA rank for diffusion fine-tuning requires balancing quality and compute cost. We present a controlled study on CIFAR-10 using a DDPM U-Net with ranks {2,4,8,16,32}, fi…
cs.CL2026
LoRA-Diffusion: Parameter-Efficient Fine-Tuning via Low-Rank Trajectory Decomposition
Iman Khazrak, Narges Nejad, Mohammadhossein Homaei +2
Parameter-efficient fine-tuning methods such as LoRA have transformed the adaptation of large autoregressive language models, enabling task-specific customization with substantiall…