2 papers
cs.SI2026
Rewarding Engagement and Personalization in Popularity-Based Rankings Amplifies Extremism and Polarization
Jacopo D'Ignazi, Emma Fraxanet Morales, Andreas Kaltenbrunner +5
Despite extensive research, the mechanisms through which online platforms shape extremism and polarization remain poorly understood. We identify and test a mechanism, grounded in e…
cs.AI2026
From Next Token Prediction to (STRIPS) World Models
Carlos Núñez-Molina, Vicenç Gómez, Hector Geffner
We study whether next-token prediction can yield world models that truly support planning, in a controlled symbolic setting where propositional STRIPS action models are learned fro…