Author

Vinicius C. Azevedo

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

Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows

This work introduces Contrastive Noise Alignment (CNA), a training-time method that creates dynamic, contrastive couplings by optimizing the noise representations directly, and shows theoretically that this equilibrium asymptotically preserves Gaussian structures, maintaining tractability during inference.

Lennart Wittke, Vinicius C. Azevedo · 0 citations