Author

Iman Khazrak

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

Adaptive gradient-norm weighting for improved domain adversarial training

Adaptive Gradient-Norm Weighting (AWD), a lightweight scalarization mechanism that dynamically adjusts gradient norms of the classification and alignment losses in UDA consistently improves average performance over fixed and scheduled baselines, with the strongest gains on more difficult transfer settings.

Iman Khazrak, Mohammadhossein Homaei, Mostafa M. Rezaee et al. · International Journal of Dat... · 0 citations

#artificial intelligence Preprint Sep 2026

Understanding LoRA Rank Trade-offs in Diffusion Model Fine-Tuning

Results show moderate ranks are most efficient: rank 4 achieves the best DDPM FID, rank 8 is close, and higher ranks provide limited gains despite larger adaptation cost, support small-to-moderate ranks as practical defaults under fixed training budgets.

Iman Khazrak, N. Nejad, Mostafa M. Rezaee et al. · 0 citations