Skip to content

Author

André Freitas

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

World Modeling in Transformers

TaxiGPT, a transformer trained on random walks through Manhattan whose failures have been interpreted as evidence of an incoherent internal map, is demonstrated, through mechanistic analysis and causal interventions, that the model represents intersections and streets, tracks its position, and uses a goal compass to na...

P. Beckmann, Matthieu Queloz, André Freitas · 0 citations
Preprint Aug 2026

Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation

Coherentist Probabilistic Compositionalism (CPC), an interpretive framework that grounds transformer computation in coherentist theories of interpretation and describes it through four operator roles, is introduced.

N. Aljaafari, André Freitas · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.