Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution

Published in 40th Conference on Neural Information Processing Systems (NeurIPS 2026), 2026

Dmytro Rizdvanetskyi, Nathan Roos, Pavlo Lutsik

We propose data-driven soft labels that estimate the conditional cell-type distribution for each read DNA, and integrate this scheme into Syto, a new modular framework for read-level classification-based cell-type deconvolution.

How I Met Your Bias: Investigating Bias Amplification in Diffusion Models

Published in 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

Nathan Roos, Ani Gjergji, Ekaterina Iakovleva, Vito Paolo Pastore and Enzo Tartaglione

For the first time, we show that sampling hyperparameters influence bias amplification in diffusion models during the inference process, across sampling algorithms, datasets, and model architectures.