I would like to think I publish pretty well for my field and access to resources (PNAS, Neuron, etc), but none of those journals have offered anything beyond word-level editing (e.g., change sec to s; replace `subjects` with `participants`) to match the house style.

I certainly didn't get any suggestions aimed at improving the readability of the text; those mostly came from coauthors and colleagues before submission, with a few more things flagged, in passing, by peer reviewers.

That's on the biology side of things. For ML, it's basically "Here's the doc class! Good luck!"