Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Guided Diffusion by Optimized Loss Functions on Relaxed Parameters for Inverse Material Design
Jens U. Kreber, Christian Weißenfels, Joerg Stueckler
Inverse design problems are common in engineering and materials science. The forward direction, i.e., computing output quantities from design parameters, typically requires running…
cs.LG2021
Generating Symbolic Reasoning Problems with Transformer GANs
Jens U. Kreber, Christopher Hahn
We study the capabilities of GANs and Wasserstein GANs equipped with Transformer encoders to generate sensible and challenging training data for symbolic reasoning domains. We cond…