New paper out from group in Heidelberg that has some extension of the work Johann Brehmer & I did on Manifold-learning flows, but for unrestricted (aka non-invertible) auto-encoders. They also suggest a different way to avoid a failure mode we identified arxiv.org/abs/2306.01843

Excited to present our fast and effective new generative model for data living on manifolds at #NeurIPS today! Manifold Free-Form Flows are simple to set up and generate data about 100x faster than the competition. Drop by poster #2710 East today at 11am-1pm to learn more!