Reversible Deep Equilibrium Models(arxiv.org)3 points·by impossiblefork·10 mesi fa·1 commentsarxiv.orgReversible Deep Equilibrium Modelshttps://arxiv.org/abs/2509.129171 commentsPost comment[–]impossiblefork·10 mesi fareplyI saw this neat paper, which proposes a more practical way to train models whose output are the fixed point of a learned function and thought it would be reasonable to talk about.They use the trick from Feistel ciphers for reversibility.
They use the trick from Feistel ciphers for reversibility.