Comment by energy123 2 months ago Yeah, once it gets converted into tokens how does "zooming in" somehow increase information content? 1 comment energy123 Reply nutrientharvest 2 months ago It's cropping the original image then tokenizing it again with less downsampling, not cropping its internal representation.
nutrientharvest 2 months ago It's cropping the original image then tokenizing it again with less downsampling, not cropping its internal representation.
It's cropping the original image then tokenizing it again with less downsampling, not cropping its internal representation.