The BERT study spans less than one decade, so its log axis carried the
wide "6 x 10^-1" tick labels, which pushed the y label off the canvas.
Give that axis plain decimal ticks and widen the axes margin of every
result figure by the same amount, which keeps the axes box identical
across figures at the 4:3 ratio.
Enlarge the in-canvas fonts and line weights of the result figures so
that they stay legible at the printed column width, split the Fig. 5
convergence curve into a pre-meta adaptation entry and the proposed
MAML entry, and rename the autoencoder legend to match the table row.
Add the analytic complexity replot behind Fig. 4, which was missing
from the repository, and correct the table numbering in the README.
KiHoLee