Author name: Ayoub Hammal, Pierre Zweigenbaum, Caio Corro

arXiv:2604.16146v2 Announce Type: replace
Abstract: Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned) model. The implicit reward approach skews the l…

arXiv:2604.16146v1 Announce Type: new
Abstract: Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned) model. The implicit reward approach skews the large…