Comment Comment by diyer22 Exactly what i think!- The DDN single-shot generator architecture is more efficient than diffusion.- DDN is fully end-to-end differentiable, allowing for more efficient optimization when integrated with discriminative models or reinforcement learning.- Moreover, DDN inherently avoids mode collapse.These points are all mentioned in the blog: https://github.com/Discrete-Distribution-Networks/Discrete-D... parent diyer22 1 year ago
- The DDN single-shot generator architecture is more efficient than diffusion.
- DDN is fully end-to-end differentiable, allowing for more efficient optimization when integrated with discriminative models or reinforcement learning.
- Moreover, DDN inherently avoids mode collapse.
These points are all mentioned in the blog: https://github.com/Discrete-Distribution-Networks/Discrete-D...