2 papers
cs.CV2025
Reflection Removal through Efficient Adaptation of Diffusion Transformers
Daniyar Zakarin, Thiemo Wandel, Anton Obukhov +1
We introduce a diffusion-transformer (DiT) framework for single-image reflection removal that leverages the generalization strengths of foundation diffusion models in the restorati…
cs.LG2025
Accelerating Neural Network Training Along Sharp and Flat Directions
Daniyar Zakarin, Sidak Pal Singh
Recent work has highlighted a surprising alignment between gradients and the top eigenspace of the Hessian -- termed the Dominant subspace -- during neural network training. Concur…