3 papers
cs.CL2026
On Compositional Learning Behaviours in Formal Mathematics
Kevin Yandoka Denamganaï
Self-evolving scientific agents capable of conquering the hard tail of formal mathematics require Compositional Learning Behaviours (CLBs) -- the capacity to ground and recombine n…
cs.CL2026
Language Model Inversion through End-to-End Differentiation
Kevin Yandoka Denamganaï, Kartic Subr
Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determinin…
cs.AI2020
A Comparison of Self-Play Algorithms Under a Generalized Framework
Daniel Hernandez, Kevin Denamganai, Sam Devlin +2
Throughout scientific history, overarching theoretical frameworks have allowed researchers to grow beyond personal intuitions and culturally biased theories. They allow to verify a…