Our approach is based on a keyobservation about human speech: there isoften ashort pause between each sentence orword.

Moreover, we utilize amino acid replacement matrices for the diffusion forward process, encoding the biologically meaningful prior knowledge of amino acids from their spatial and sequential neighbors as well as themselves, which reduces the sampling space of the generative process.

Theproblemcontainsa prompt (blue), acanonicalsolutiontotheprompt (green), andafewtest-cases (black).