6 citations · 8 across the 7 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
An equality condition for the Dobrushin bound on attention rollout and how often it holds in trained transformers
Przemysław Rola
The Dobrushin coefficient of each attention-rollout factor satisfies , and multiplying these inequalities over layers bounds the coefficient of t…
cs.LG2026
EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning
Przemysław Rola
We introduce EntroPath, a manifold learning method that recovers geodesic geometry from data graphs through ensembles of diffusion paths. Many existing graph-based embeddings rely…
cs.LG2023
Contrastive Hierarchical Clustering
Michał Znaleźniak, Przemysław Rola, Patryk Kaszuba +2
Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the g…