2 papers
cs.AI2026
Reproducing and Evaluating the Generalizability of Subliminal Learning in Open-Weight Models
Daan van der Weijden, Nathan Brack, Selene Baez Santamaria
In this reproduction paper we investigate subliminal learning, a consequence of distillation where teacher models transmit behavioral preference traits through semantically unrelat…
cs.SI2025
Graph Neural Networks for Source Detection: A Review and Benchmark Study
Martin Sterchi, Nathan Brack, Lorenz Hilfiker
The source detection problem arises when an epidemic process unfolds over a contact network, and the objective is to identify its point of origin, i.e., the source node. Research o…