Generative Models: Principles, Architectures, and Applications
Jun Lu
cs.AI
Submitted: 2026-08-08
Updated: 2026-08-11
Code: https://github.com/black-forest-labs/flux
License: http://creativecommons.org/licenses/by/4.0/
The gist: Generative AI has emerged as one of the most transformative forces in modern artificial intelligence, reshaping how we create, imagine, and interact with digital content.
Terminology
Abstract
Generative AI has emerged as one of the most transformative forces in modern artificial intelligence, reshaping how we create, imagine, and interact with digital content. From photorealistic images to coherent text, from immersive videos to novel molecular structures, generative models now power applications that were once confined to science fiction. This book is designed to guide readers through the foundational principles, mathematical underpinnings, and practical architectures that underpin this revolution.
Sources
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- WaveGrad: Estimating Gradients for Waveform Generation
- NICE: Non-linear Independent Components Estimation
- Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- Classifier-Free Diffusion Guidance
- An Introduction to Flow Matching and Diffusion Models
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- Flow Matching for Generative Modeling
- Flow Matching Guide and Code
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Numerical Matrix Decomposition
- A rigorous introduction to linear models
- A survey on Bayesian inference for Gaussian mixture model
- Gradient Descent, Stochastic Optimization, and Other Tales
- Matrix Decomposition and Applications
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems