Generative Modeling Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Modern generative modeling connects latent-variable inference, invertible transformations, and score estimation. These ten papers are the backbone—VAEs, flows, and the score-based view that underpins diffusion.

Generative Modeling: 10 key papers

1. Stochastic Backpropagation and Approximate Inference in Deep Generative Models
   Rezende et al. arXiv 2014.
2. Generative Adversarial Networks
   Goodfellow et al. arXiv 2014.
3. NICE: Non-linear Independent Components Estimation
   Dinh et al. arXiv 2014.
4. Density estimation using Real NVP
   Dinh et al. arXiv 2016.
5. Glow: Generative Flow with Invertible 1x1 Convolutions
   Kingma and Dhariwal. arXiv 2018.
6. Normalizing Flows for Probabilistic Modeling and Inference
   Papamakarios et al. arXiv 2019.
7. Neural Discrete Representation Learning
   van den Oord et al. arXiv 2017.
8. Pixel Recurrent Neural Networks
   van den Oord et al. arXiv 2016.
9. Conditional Image Generation with PixelCNN Decoders
   van den Oord et al. arXiv 2016.
10. A Style-Based Generator Architecture for Generative Adversarial Networks
    Karras et al. arXiv 2018.

Related reading lists

• Score-Based Generative Modeling
• Flow Matching & Schrödinger Bridges
• Diffusion Models & Score-Based Generative Models
• Diffusion Models for Decision Making
• Variational Inference & ELBO
• Bayesian Deep Learning
• Neural Architecture Search
• Imitation Learning and Inverse RL