Pandaemonium Architecture 6.0

In this course

Brock is a machine learning researcher at Heriot-Watt University who co-authored foundational work on scaling generative adversarial networks (GANs) for high-fidelity image synthesis, addressing the critical challenge of training stability and sample quality at scale. His work on the quality-diversity trade-off in generative models—particularly the variety-fidelity curve—provides conceptual tools for understanding how diffusion and GAN-based systems navigate the fundamental tension between creative diversity and technical fidelity, a key concern for artistic and experimental applications of generative AI.

Mentioned in 2 readings

Andrew Brock

et al., LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS

2

Large Scale GAN Training for High Fidelity Natural Image Synthesis Andrew Brock\† Heriot-Watt University ajb5@hw.ac.uk Jeff Donahue† DeepMind jeffdonahue@google.com Karen Simonyan† DeepMind simonyan@google.com Abstract Despite recent p…This technique allows fine-grained, post-hoc selection of the trade-off between sample quality and variety for a given G. Notably, we can compute FID and IS for a range of thresholds, obtaining the variety-fidelity curve reminiscent of the …

Robin Rombach

et al., High-Resolution Image Synthesis with Latent Diffusion Models

1

6. Conclusion We have presented latent diffusion models, a simple and efficient way to significantly improve both the training and sampling efficiency of denoising diffusion models without degrading their quality. Based on this and our cro…

Appears alongside

People mentioned in the same passages — sorted by co-occurrence weight.