David Mildenberger — accepted AI-conference papers

2026

Step-resolved data attribution for looped transformers

Georgios Kaissis, David Mildenberger, Felipe Gomez, Martin Menten, Eleni Triantafillou

ICML 2026poster

We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for $\tau$ recurrent iterations to enable latent reasoning. Existing training-data influence estimators such as TracIn yield a single scalar score that aggregates over all…

Cited by 0 Source ↗Scholar ↗

2025

A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets

David Mildenberger, Paul Hager, Daniel Rueckert, Martin J. Menten

CVPR 2025poster

Supervised contrastive learning (SupCon) has proven to be a powerful alternative to the standard cross-entropy loss for classification of multi-class balanced datasets. However, it struggles to learn well-conditioned representations of datasets with long-tailed class distributions. This problem is p…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗