2 papers
cs.LG2026
Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization
Filipe Marinho Rocha, Inês Dutra, Vítor Santos Costa +1
A model generalizes outside its training distribution only when it computes a representation structurally equivalent to the generating mechanism, not an approximation fitted to it.…
cs.LG2024
Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus
Filipe Marinho Rocha, Inês Dutra, Vítor Santos Costa
The Abstraction and Reasoning Corpus (ARC) is a general artificial intelligence benchmark that is currently unsolvable by any Machine Learning method, including Large Language Mode…