The general strategy of creating a differentiable representation of a problem and simply describing the constraints is pretty powerful. See also databases (allowing arbitrary knowledge storage to be a tightly integrated part of a larger ML problem), graph layouts (you can do _way_ better than something like graphviz if you add arbitrary differentiable characteristics as constraints in generation -- mixing and matching between the better parts of normal layout routines using your human intuition to say what's important about this graph in particular), ....
Very cool!
Extremely related to this, which focuses more on integrating architectural design constraints:
http://www.rewdesign.ch/automated-floorplan-generation-in-ar...
https://www.researchgate.net/publication/380319243_A_hypergr...
This is fascinating to me because I once tried to take a (vaguely) similar approach to generate a procedural city layout, taking a voronoi diagram, and then doing some modified flood fills to create buildings within the city while leavings streets.
It feels to me like their approach could be used for this as well, since there's of course nothing that requires it to only be used for generating floor plans.
This will be great for deciding on voting districts
Really cool. Could see this being used for generative video game assets