Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't

ArXi:2605.30523v1 Announce Type: cross Recent work describes what transformers can and cannot compute through connections to boolean circuits, but existing results lack exact characterizations and are sensitive to modeling choices. Padded transformers -- to whose input filler symbols such as are appended -- emerge as a useful gadget for establishing equivalences to circuit classes by providing polynomial space for adaptive parallel computation.