Decomposing Antonyms?

Are the marked members of antonym-pairs such as long – short decomposed in the syntax? Büring has recently argued that they are, on the basis of evidence about the distribution of Rullmann-ambiguities and crosspolar anomalies. But the readings of marked antonyms in the complements of matrix modals seem to argue for the opposite conclusion. The dilemma that results defies a simple solution. Perhaps it tells us something about the workings of Comparative Deletion.