I'm working on a totally new adversarial approach (not just a modified loss or small trick) and its working very well right off the bat without tuned hyperpameters. This one is going make a great publication. I won't be able to make in time for #NeurIPS though. Stay tuned! 
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.