[diyer22]

In DDN, 1×1 convolutions are used only in the output layers of the Discrete Distribution Layer (DDL). The NN blocks between DDLs, which supply the fundamental computational power and parameter count, adopt standard 3×3 convolutions.

[randomNumber7]

Was there a specific reason for this choice?

[diyer22]

1x1 convolution is the most lightweight operator for transforming features into outputs.

3x3 convolution is the most common operator used to provide basic computational power.