Learning path for the diffusion model
- Estimation of Non-Normalized Statistical Models by Score Matching [paper]
- A Connection Between Score Matching and Denoising Autoencoders [paper]
- A Kernelized Stein Discrepancy for Goodness-of-fit Tests [Paper]
- Sliced Score Matching: A Scalable Approach to Density and Score Estimation [Paper]
- Bayesian Learning via Stochastic Gradient Langevin Dynamics [paper]
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics (ICML 2015) [Paper] [Video]
- Generative Modeling by Estimating Gradients of the Data Distribution (NeurLPS 2019) [Paper] [Youtube] [youtube] [知乎] [知乎][Blog]
- Improved Techniques for Training Score-BasedGenerative Models (NeurLPS 2020) [Paper] [Github]
- Denoising Diffusion Probabilistic Models (NeurIPS 2020) [Paper] [知乎] [Blog] [Youtube] [Github]
- Denoising Diffusion Implicit Models (ICLR 2021) [Paper] [Github]
- Improved Denoising Diffusion Probabilistic Models [ICML 2021] [Paper] [Github]
- Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021) [Paper] [Github] [Blog] [Video] [Video] [video]
- Diffusion Models Beat GANs on Image Synthesis (NeurIPS 2021) [Paper] [Github] [Video]
- Score-based Generative Modeling in Latent Space (NeurIPS 2021) [Paper] [Github] [Project] [Video]
- Cascaded Diffusion Models for High Fidelity Image Generation （Arxiv 2021）[Paper]
- Classifier-Free Diffusion Guidance （NeurIPS 2021, ICLR 2022） [Paper] [Paper] [Github]
- High-Resolution Image Synthesis with Latent Diffusion Models (CVPR 2022) [Paper] [Github]
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models (ICML 2022) [Paper][Tensorflow] [Pytorch]
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps (NeurIPS 2022) [Paper] [Gitihub]
- Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (NeurIPS 2022) [Paper] [Github]
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation (CVPR 2023) [Paper] [Project] [Github]