2 Comments
User's avatar
Alexander Veysov's avatar

Well, GANs were not a fad per se, but they found their place as a niche tool for generative tasks. Over-investment into GAN papers was a fad, true.

Expand full comment
daniel bashir's avatar

Fair enough, that seems closer to the truth—definitely an over-investment. It seems like there were some important lessons to learn from working on GANs, but those lessons didn’t require quite as much investment as they got

Expand full comment