Generative models

Compute interpretation

VAE, GAN, autoregressive, and image-generation methods whose practical form depends on accelerator throughput and sampling cost.

Supporting reading cards

• Auto-Encoding Variational Bayes (2013, generative_media_compute)
• Generative Adversarial Nets (2014, generative_media_compute)
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (2015, generative_media_compute)
• Image-to-Image Translation with Conditional Adversarial Networks (2016, generative_media_compute)
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (2017, generative_media_compute)
• A Style-Based Generator Architecture for Generative Adversarial Networks (2018, generative_media_compute)
• Denoising Diffusion Probabilistic Models (2020, generative_media_compute)
• Score-Based Generative Modeling through Stochastic Differential Equations (2020, generative_media_compute)
• High-Resolution Image Synthesis with Latent Diffusion Models (2021, generative_media_compute)
• Zero-Shot Text-to-Image Generation (2021, generative_media_compute)
• Improved Denoising Diffusion Probabilistic Models (2021, generative_media_compute)
• Scalable Diffusion Models with Transformers (2022, generative_media_compute)
• Qwen3.5-Omni Technical Report (2026, generative_media_compute)

Obsolete or less central under later compute

Track this only through linked reading cards; do not treat this method page as standalone evidence.