Author

Keshab K. Parhi

1 paper 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.

#machine learning Preprint Sep 2026

DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning

Diffusion-Conditioned Representation Alignment (DCRA), a training framework that repurposes the forward diffusion process as a structured corruption scheduler for representation learning, and produces more balanced and structured representations compared to baseline and diffusion-only models.

Wen-Rui Xu, Anas Enanaa, Keshab K. Parhi · 0 citations