{"id":15121452,"url":"https://github.com/yangling0818/diffusion-models-papers-survey-taxonomy","last_synced_at":"2025-05-14T03:07:15.775Z","repository":{"id":59164563,"uuid":"535691024","full_name":"YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy","owner":"YangLing0818","description":"Diffusion model papers, survey, and taxonomy","archived":false,"fork":false,"pushed_at":"2025-02-27T00:55:16.000Z","size":279,"stargazers_count":3157,"open_issues_count":8,"forks_count":263,"subscribers_count":54,"default_branch":"main","last_synced_at":"2025-04-10T20:54:47.683Z","etag":null,"topics":["diffusion-models","stable-diffusion","survey","text-to-3d","text-to-image","text-to-video"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YangLing0818.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-09-12T13:54:01.000Z","updated_at":"2025-04-10T17:50:10.000Z","dependencies_parsed_at":"2023-01-30T21:46:02.558Z","dependency_job_id":"ae7cd472-ce85-4a06-a8fb-920cdb527725","html_url":"https://github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YangLing0818%2FDiffusion-Models-Papers-Survey-Taxonomy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YangLing0818%2FDiffusion-Models-Papers-Survey-Taxonomy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YangLing0818%2FDiffusion-Models-Papers-Survey-Taxonomy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YangLing0818%2FDiffusion-Models-Papers-Survey-Taxonomy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YangLing0818","download_url":"https://codeload.github.com/YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254059501,"owners_count":22007768,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["diffusion-models","stable-diffusion","survey","text-to-3d","text-to-image","text-to-video"],"created_at":"2024-09-26T02:00:56.599Z","updated_at":"2025-05-14T03:07:15.704Z","avatar_url":"https://github.com/YangLing0818.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Diffusion Models: A Comprehensive Survey of Methods and Applications\nThis repo is constructed for collecting and categorizing papers about diffusion models according to our survey paper——[_**Diffusion Models: A Comprehensive Survey of Methods and Applications**_](https://arxiv.org/abs/2209.00796), which has been accepted by the journal **ACM Computing Surveys**. Considering the fast development of this field, we will continue to update **both [arxiv paper](https://arxiv.org/abs/2209.00796) and this repo**.\n# Overview\n\u003cdiv aligncenter\u003e\u003cimg width=\"900\" alt=\"image\" src=\"https://user-images.githubusercontent.com/62683396/227244860-3608bf02-b2af-4c00-8e87-6221a59a4c42.png\"\u003e\n\n# Catalogue\n## [Algorithm Taxonomy](#1)\n### [Sampling-Acceleration Enhancement](#1.1)\n  - [Learning-Free Sampling](#1.1.1)\n    - [SDE Solver](#1.1.1.1)\n    - [ODE Solver](#1.1.1.2)\n  - [Learning-Based Sampling](#1.1.2)\n    - [Optimized Discretization](#1.1.2.1)\n    - [Knowledge Distillation](#1.1.2.2)\n    - [Truncated Diffusion](#1.1.2.3)\n### [Likelihood-Maximization Enhancement](#1.2)\n  - [Noise Schedule Optimization](#1.2.1)\n  - [Reverse Variance Learning](#1.2.2)\n  - [Exact Likelihood Computation](#1.2.3)\n### [Data with Special Structures](#1.3)\n  - [Data with Manifold Structures](#1.3.1)\n    - [Known Manifolds](#1.3.1.1)\n    - [Learned Manifolds](#1.3.1.2)\n  - [Data with Invariant Structures](#1.3.2)\n  - [Discrete Data](#1.3.3)\n### [Diffusion with (Multimodal) LLM](#1.4)\n  - [Simple Combination](#1.4.1)\n  - [Deep Collaboration](#1.4.2)\n### [Diffusion with DPO/RLHF](#1.5)\n\n## [Application Taxonomy](#2)\n* [Computer Vision](#2.1)\n  - [Image Super Resolution, Inpainting and Translation](#2.1.1)\n  - [Semantic Segementation](#2.1.2)\n  - [Video Generation](#2.1.3)\n  - [3D Generation](#2.1.4)\n  - [Anomaly Detection](#2.1.5)\n  - [Object Detection](#2.1.6)\n* [Natural Language Processing](#2.2)\n* [Temporal Data Modeling](#2.3)\n  - [Time-Series Imputation](#2.3.1)\n  - [Time-Seires Forecasting](#2.3.2)\n  - [Waveform Signal Processing](#2.3.3)\n* [Multi-Modal Learning](#2.4)\n  - [Text-to-Image Generation](#2.4.1)\n  - [Text-to-3D Generation](#2.4.2)\n  - [Scene Graph/Layout to Image Generation](#2.4.3)\n  - [Text-to-Audio Generation](#2.4.4)\n  - [Text-to-Motion Generation](#2.4.5)\n  - [Text-to-Video Generation/Editting](#2.4.6)\n* [Robust Learning](#2.5)\n  - [Data Purification](#2.5.1)\n  - [Generating Synthetic Data for Robust Learning](#2.5.2)\n* [Molecular Graph Modeling](#2.6)\n* [Material Design](#2.7)\n* [Medical Image Reconstruction](#2.8)\n\n\n\n## [Connections with Other Generative Models](#3)\n* [Variational Autoencoder](#3.1)\n* [Generative Adversarial Network](#3.2)\n* [Normalizing Flow](#3.3)\n* [Autoregressive Models](#3.4)\n* [Energy-Based Models](#3.5)\n\n\u003cp id=\"1\"\u003e\u003c/p \u003e\n\n## Algorithm Taxonomy\n\u003cp id=\"1.1\"\u003e\u003c/p \u003e\n\n### 1. Efficient Sampling\n\u003cp id=\"1.1.1\"\u003e\u003c/p \u003e\n\n#### 1.1 Learning-Free Sampling\n\u003cp id=\"1.1.1.1\"\u003e\u003c/p \u003e\n\n##### 1.1.1 SDE Solver\n\n[Score-Based Generative Modeling\nthrough Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS)\n\n[Adversarial score matching and improved sampling for image generation](https://openreview.net/forum?id=eLfqMl3z3lq)\n\n[Come-closer-diffuse-faster: Accelerating conditional diffusion models for inverse\nproblems through stochastic contraction](https://openaccess.thecvf.com/content/CVPR2022/html/Chung_Come-Closer-Diffuse-Faster_Accelerating_Conditional_Diffusion_Models_for_Inverse_Problems_Through_Stochastic_CVPR_2022_paper.html)\n\n\n[Score-Based Generative Modeling with Critically-Damped Langevin Diffusion](https://openreview.net/forum?id=CzceR82CYc)\n\n[ Gotta Go Fast When Generating Data with\nScore-Based Models](https://arxiv.org/abs/2105.14080)\n\n[Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364)\n\n[Generative modeling by estimating gradients of the data distribution](https://proceedings.neurips.cc/paper/2019/hash/3001ef257407d5a371a96dcd947c7d93-Abstract.html)\n\n[Structure-Guided Adversarial Training of Diffusion Models](https://arxiv.org/abs/2402.17563)\n\u003cp id=\"1.1.1.2\"\u003e\u003c/p \u003e\n\n##### 1.1.2 ODE Solver\n[Denoising Diffusion Implicit Models](https://openreview.net/forum?id=St1giarCHLP)\n\n[Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n\n[gDDIM: Generalized denoising diffusion implicit models](https://arxiv.org/abs/2206.05564)\n\n[Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364)\n\n\n[DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model\nSampling in Around 10 Step](https://arxiv.org/abs/2206.00927)\n\n[Pseudo Numerical Methods for Diffusion Models on Manifolds](https://openreview.net/forum?id=PlKWVd2yBkY)\n\n[Fast Sampling of Diffusion Models with Exponential Integrator](https://arxiv.org/abs/2204.13902)\n\n[Poisson flow generative models](https://openreview.net/pdf?id=voV_TRqcWh)\n\n[Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n\n[Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing](https://openreview.net/forum?id=nFMS6wF2xq)\n\n[Structure-Guided Adversarial Training of Diffusion Models](https://arxiv.org/abs/2402.17563)\n\n[Consistency Flow Matching: Defining Straight Flows with Velocity Consistency](https://arxiv.org/abs/2407.02398v1)\n\n[Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening](https://arxiv.org/abs/2502.12146)\n\u003cp id=\"1.1.2\"\u003e\u003c/p \u003e\n\n#### 1.2 Learning-Based Sampling\n\u003cp id=\"1.1.2.1\"\u003e\u003c/p \u003e\n\n##### 1.2.1 Optimized Discretization\n[Learning to Efficiently Sample from Diffusion Probabilistic Models](https://arxiv.org/abs/2106.03802)\n\n[GENIE: Higher-Order Denoising Diffusion Solvers](https://arxiv.org/abs/2210.05475)\n\n[Learning fast samplers for diffusion models by differentiating through\nsample quality](https://openreview.net/forum?id=VFBjuF8HEp)\n\u003cp id=\"1.1.2.2\"\u003e\u003c/p \u003e\n\n##### 1.2.2 Knowledge Distillation\n[Progressive Distillation for Fast Sampling of Diffusion Models](https://openreview.net/forum?id=TIdIXIpzhoI)\n\n[Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed](https://arxiv.org/abs/2101.02388)\n\n[Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening](https://arxiv.org/abs/2502.12146)\n\u003cp id=\"1.1.2.3\"\u003e\u003c/p \u003e\n\n##### 1.2.3 Truncated Diffusion\n[Accelerating Diffusion Models via Early Stop of the Diffusion Process](https://arxiv.org/abs/2205.12524)\n\n[Truncated Diffusion Probabilistic Models](https://arxiv.org/abs/2202.09671)\n\u003cp id=\"1.2\"\u003e\u003c/p \u003e\n\n### 2. Improved Likelihood\n\u003cp id=\"1.2.1\"\u003e\u003c/p \u003e\n\n#### 2.1. Noise Schedule Optimization\n\n[Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing](https://openreview.net/forum?id=nFMS6wF2xq)\n\n[ Improved denoising diffusion probabilistic models](https://proceedings.mlr.press/v139/nichol21a.html)\n\n[Variational diffusion models](https://proceedings.neurips.cc/paper/2021/hash/b578f2a52a0229873fefc2a4b06377fa-Abstract.html)\n\u003cp id=\"1.2.2\"\u003e\u003c/p \u003e\n\n#### 2.2. Reverse Variance Learning\n[Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models](https://openreview.net/forum?id=0xiJLKH-ufZ)\n\n[ Improved denoising diffusion probabilistic models](https://proceedings.mlr.press/v139/nichol21a.html)\n\n[Stable Target Field for Reduced Variance Score Estimation in Diffusion Models](https://openreview.net/forum?id=WmIwYTd0YTF)\n\u003cp id=\"1.2.3\"\u003e\u003c/p \u003e\n\n#### 2.3. Exact Likelihood Computation\n[Structure-Guided Adversarial Training of Diffusion Models](https://arxiv.org/abs/2402.17563)\n\n[Score-Based Generative Modeling\nthrough Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS)\n\n[Maximum likelihood training of score-based diffusion models](https://proceedings.neurips.cc/paper/2021/hash/0a9fdbb17feb6ccb7ec405cfb85222c4-Abstract.html)\n\n[A variational perspective on diffusion-based generative models and score matching](https://proceedings.neurips.cc/paper/2021/hash/c11abfd29e4d9b4d4b566b01114d8486-Abstract.html)\n\n[Score-Based Generative Modeling\nthrough Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS)\n\n[ Maximum Likelihood Training for Score-based Diffusion\nODEs by High Order Denoising Score Matching](https://proceedings.mlr.press/v162/lu22f.html)\n\n[Maximum Likelihood Training of Implicit Nonlinear Diffusion Models](https://openreview.net/forum?id=TQn44YPuOR2)\n\n[Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n\u003cp id=\"1.3\"\u003e\u003c/p \u003e\n\n### 3. Data with Special Structures\n\u003cp id=\"1.3.1\"\u003e\u003c/p \u003e\n\n#### 3.1. Data with Manifold Structures\n\u003cp id=\"1.3.1.1\"\u003e\u003c/p \u003e\n\n##### 3.1.1 Known Manifolds\n\n[Riemannian Score-Based Generative\nModeling](https://arxiv.org/abs/2202.02763)\n\n[Riemannian Diffusion Models](https://arxiv.org/abs/2208.07949)\n\u003cp id=\"1.3.1.2\"\u003e\u003c/p \u003e\n\n##### 3.1.2 Learned Manifolds\n[Score-based generative modeling in latent space](https://proceedings.neurips.cc/paper/2021/hash/5dca4c6b9e244d24a30b4c45601d9720-Abstract.html)\n\n[ Diffusion priors in variational autoencoders](https://orbi.uliege.be/handle/2268/262334)\n\n[ Hierarchical text-conditional image generation with clip latents](https://arxiv.org/abs/2204.06125)\n\n[High-resolution image synthesis with latent diffusion\nmodels](https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html)\n\n[Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n\u003cp id=\"1.3.2\"\u003e\u003c/p \u003e\n\n#### 3.2. Data with Invariant Structures\n[ GeoDiff: A Geometric Diffusion Model for Molecular\nConformation Generation](https://openreview.net/forum?id=PzcvxEMzvQC)\n\n[Permutation invariant graph generation via\nscore-based generative modeling](http://proceedings.mlr.press/v108/niu20a)\n\n[Score-based Generative Modeling of Graphs via\nthe System of Stochastic Differential Equations](https://proceedings.mlr.press/v162/jo22a.html)\n  \n[DiGress: Discrete Denoising diffusion for graph generation](https://arxiv.org/abs/2209.14734)\n\n[Learning gradient fields for molecular conformation generation](http://proceedings.mlr.press/v139/shi21b.html)\n \n[Graphgdp: Generative diffusion processes for permutation invariant graph generation](https://arxiv.org/abs/2212.01842)\n\n[SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation](https://arxiv.org/abs/2307.01646)\n\n[Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models](https://openreview.net/forum?id=qH9nrMNTIW)\n\n[Graphusion: Latent Diffusion for Graph Generation](https://ieeexplore.ieee.org/abstract/document/10508504)\n  \n\u003cp id=\"1.3.3\"\u003e\u003c/p \u003e\n\n#### 3.3 Discrete Data\n[Vector quantized diffusion model\nfor text-to-image synthesis](https://openaccess.thecvf.com/content/CVPR2022/html/Gu_Vector_Quantized_Diffusion_Model_for_Text-to-Image_Synthesis_CVPR_2022_paper.html)\n\n[Structured Denoising Diffusion Models in Discrete\nState-Spaces](https://proceedings.neurips.cc/paper/2021/hash/958c530554f78bcd8e97125b70e6973d-Abstract.html)\n\n[Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign\nPose Sequences Generation](https://arxiv.org/abs/2208.09141)\n\n[Deep Unsupervised Learning using Non equilibrium\nThermodynamics.](https://openreview.net/forum?id=rkbVIoZdWH)\n\n[A Continuous Time Framework\nfor Discrete Denoising Models](https://arxiv.org/abs/2205.14987)\n\u003cp id=\"1.4\"\u003e\u003c/p \u003e\n\n### 4. Diffusion with (Multimodal) LLM\n\u003cp id=\"1.4.1\"\u003e\u003c/p \u003e\n\n#### 4.1. Simple Combination\n[LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://arxiv.org/abs/2305.13655)\n\n[Videodirectorgpt: Consistent multi-scene video generation via llm-guided planning](https://arxiv.org/abs/2309.15091)\n\n[RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models](https://arxiv.org/abs/2402.12908)\n\u003cp id=\"1.4.2\"\u003e\u003c/p \u003e\n\n#### 4.2. Deep Collaboration\n[Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://arxiv.org/abs/2401.11708)\n\n[VideoTetris: Towards Compositional Text-To-Video Generation](https://arxiv.org/abs/2406.04277)\n\u003cp id=\"1.5\"\u003e\u003c/p \u003e\n\n### 4. Diffusion with DPO/RLHF\n[Diffusion Model Alignment Using Direct Preference Optimization](https://arxiv.org/abs/2311.12908)\n\n[ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://arxiv.org/abs/2304.05977)\n\n[IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation](https://arxiv.org/abs/2410.07171)\n\n[Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening](https://arxiv.org/abs/2502.12146)\n\u003cp id=\"2\"\u003e\u003c/p\u003e\n\n## Application Taxonomy\n\u003cp id=\"2.1\"\u003e\u003c/p\u003e\n\n### 1. Computer Vision\n\u003cp id=\"2.1.1\"\u003e\u003c/p \u003e\n\n  - Conditional Image Generation (Image Super Resolution, Inpainting, Translation, Manipulation)\n    - [Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n    - [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://www.sciencedirect.com/science/article/pii/S0925231222000522)\n    - [Image Super-Resolution via Iterative Refinement](https://openreview.net/forum?id=y4N8y8ZQ4c1)\n    - [High-Resolution Image Synthesis with Latent Diffusion Models](https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html)\n    - [Repaint: Inpainting using denoising diffusion probabilistic models.](https://openaccess.thecvf.com/content/CVPR2022/html/Lugmayr_RePaint_Inpainting_Using_Denoising_Diffusion_Probabilistic_Models_CVPR_2022_paper.html)\n    - [Palette: Image-to-image diffusion models.](https://openreview.net/forum?id=FPGs276lUeq)\n    - [Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models](http://arxiv.org/abs/2209.06970)\n    - [Cascaded Diffusion Models for High Fidelity Image Generation.](https://www.jmlr.org/papers/v23/21-0635.html)\n    - [Conditional image generation with score-based diffusion models](https://arxiv.org/abs/2111.13606)\n    - [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://arxiv.org/abs/2207.08208)\n    - [Score-based diffusion models for accelerated MRI](https://www.sciencedirect.com/science/article/pii/S1361841522001268)\n    - [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://openreview.net/forum?id=vaRCHVj0uGI)\n    - [MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion](https://arxiv.org/abs/2203.12621)\n    - [Sdedit: Guided image synthesis and editing with stochastic differential equations](https://arxiv.org/abs/2108.01073)\n    - [Soft diffusion: Score matching for general corruptions](https://web7.arxiv.org/abs/2209.05442) \n    - [Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training](https://arxiv.org/abs/2211.11138)\n    - [ControlNet: Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543)\n    - [Image Restoration with Mean-Reverting Stochastic Differential Equations](https://arxiv.org/abs/2301.11699)\n    - [SpaText: Spatio-Textual Representation for Controllable Image Generation](https://openaccess.thecvf.com/content/CVPR2023/html/Avrahami_SpaText_Spatio-Textual_Representation_for_Controllable_Image_Generation_CVPR_2023_paper.html)\n    - [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://arxiv.org/abs/2305.16311)\n    - [Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n    - [Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing](https://openreview.net/forum?id=nFMS6wF2xq)\n    - [RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models](https://arxiv.org/abs/2402.12908)\n    - [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://arxiv.org/abs/2401.11708)\n    - [EditWorld: Simulating World Dynamics for Instruction-Following Image Editing](https://arxiv.org/abs/2405.14785)\n    - [IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation](https://arxiv.org/abs/2410.07171)\n    - [Consistency Flow Matching: Defining Straight Flows with Velocity Consistency](https://arxiv.org/abs/2407.02398v1)\n    - [Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow](https://arxiv.org/abs/2410.07303)\n    - [Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening](https://arxiv.org/abs/2502.12146)\n\u003cp id=\"2.1.2\"\u003e\u003c/p \u003e\n\n  - Semantic Segmentation\n    - [ Label-Efficient Semantic Segmentation with Diffusion Models.](https://openreview.net/forum?id=SlxSY2UZQT)\n    - [Decoder Denoising Pretraining for Semantic Segmentation.](https://arxiv.org/abs/2205.11423)\n    - [Diffusion models as plug-and-play priors](https://arxiv.org/abs/2206.09012)\n\u003cp id=\"2.1.3\"\u003e\u003c/p \u003e\n\n  - Video Generation\n    - [Flexible Diffusion Modeling of Long Videos](https://arxiv.org/abs/2205.11495)\n    - [Video diffusion models](https://openreview.net/forum?id=BBelR2NdDZ5)\n    - [Diffusion probabilistic modeling for video generation](https://arxiv.org/abs/2203.09481)\n    - [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model.](https://arxiv.org/abs/2208.15001)\n    - [Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing](https://openreview.net/forum?id=nFMS6wF2xq)\n    - [Stable video diffusion: Scaling latent video diffusion models to large datasets](https://arxiv.org/abs/2311.15127)\n    - [I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models](https://arxiv.org/abs/2311.04145)\n    - [Lumiere: A space-time diffusion model for video generation](https://arxiv.org/abs/2401.12945)\n    - [VideoTetris: Towards Compositional Text-To-Video Generation](https://arxiv.org/abs/2406.04277)\n\u003cp id=\"2.1.4\"\u003e\u003c/p \u003e\n\n  - 3D Generation\n    - [3d shape generation and completion through point-voxel diffusion](https://openaccess.thecvf.com/content/ICCV2021/html/Zhou_3D_Shape_Generation_and_Completion_Through_Point-Voxel_Diffusion_ICCV_2021_paper.html)\n    - [Diffusion probabilistic models for 3d point cloud generation](https://openaccess.thecvf.com/content/CVPR2021/html/Luo_Diffusion_Probabilistic_Models_for_3D_Point_Cloud_Generation_CVPR_2021_paper.html)\n    - [A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion](https://openreview.net/forum?id=wqD6TfbYkrn)\n    - [Let us Build Bridges: Understanding and Extending Diffusion Generative Models.](https://arxiv.org/abs/2208.14699)\n    - [LION: Latent Point Diffusion Models for 3D Shape Generation](https://arxiv.org/abs/2210.06978)\n    - [Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior](https://arxiv.org/pdf/2303.14184v2.pdf)\n    - [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Score_Jacobian_Chaining_Lifting_Pretrained_2D_Diffusion_Models_for_3D_CVPR_2023_paper.pdf)\n    - [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](https://openaccess.thecvf.com/content/CVPR2023/papers/Anciukevicius_RenderDiffusion_Image_Diffusion_for_3D_Reconstruction_Inpainting_and_Generation_CVPR_2023_paper.pdf)\n    - [HOLODIFFUSION: Training a 3D Diffusion Model using 2D Images](https://openaccess.thecvf.com/content/CVPR2023/papers/Karnewar_HOLODIFFUSION_Training_a_3D_Diffusion_Model_Using_2D_Images_CVPR_2023_paper.pdf)\n    - [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://openaccess.thecvf.com/content/CVPR2023/papers/Metzer_Latent-NeRF_for_Shape-Guided_Generation_of_3D_Shapes_and_Textures_CVPR_2023_paper.pdf)\n    - [DiffRF: Rendering-Guided 3D Radiance Field Diffusion](https://openaccess.thecvf.com/content/CVPR2023/papers/Muller_DiffRF_Rendering-Guided_3D_Radiance_Field_Diffusion_CVPR_2023_paper.pdf)\n    - [DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models](https://openaccess.thecvf.com/content/CVPR2023/papers/Wynn_DiffusioNeRF_Regularizing_Neural_Radiance_Fields_With_Denoising_Diffusion_Models_CVPR_2023_paper.pdf)\n    - [3D Neural Field Generation using Triplane Diffusion](https://openaccess.thecvf.com/content/CVPR2023/papers/Shue_3D_Neural_Field_Generation_Using_Triplane_Diffusion_CVPR_2023_paper.pdf)\n    - [Semantic Score Distillation Sampling for Compositional Text-to-3D Generation](https://arxiv.org/abs/2410.09009)\n    - [Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis](https://arxiv.org/abs/2410.07155)\n\u003cp id=\"2.1.5\"\u003e\u003c/p \u003e\n\n  - Anomaly Detection\n    - [AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise](https://openaccess.thecvf.com/content/CVPR2022W/NTIRE/html/Wyatt_AnoDDPM_Anomaly_Detection_With_Denoising_Diffusion_Probabilistic_Models_Using_Simplex_CVPRW_2022_paper.html)\n    - [Remote Sensing Change Detection (Segmentation) using Denoising Diffusion Probabilistic Models.](https://ui.adsabs.harvard.edu/abs/2022arXiv220611892G/abstract)\n\u003cp id=\"2.1.6\"\u003e\u003c/p \u003e\n\n  - Object Detection\n    - [DiffusionDet: Diffusion Model for Object Detection](https://arxiv.org/abs/2211.09788)\n\u003cp id=\"2.2\"\u003e\u003c/p\u003e\n\n### 2. Natural Language Processing\n  - [Structured denoising diffusion models in discrete state-spaces](https://proceedings.neurips.cc/paper/2021/hash/958c530554f78bcd8e97125b70e6973d-Abstract.html)\n  - [Diffusion-LM Improves Controllable Text Generation.](https://arxiv.org/abs/2205.14217)\n  - [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://arxiv.org/abs/2208.04202)\n  - [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://arxiv.org/abs/2210.08933)\n \n\u003cp id=\"2.3\"\u003e\u003c/p\u003e\n\n### 3. Temporal Data Modeling\n\u003cp id=\"2.3.1\"\u003e\u003c/p \u003e\n\n  - Time Series Imputation\n    - [CSDI: Conditional score-based diffusion models for probabilistic time series imputation](https://proceedings.neurips.cc/paper/2021/hash/cfe8504bda37b575c70ee1a8276f3486-Abstract.html)\n    - [Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models](https://arxiv.org/abs/2208.09399)\n    - [Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time Data](https://openreview.net/forum?id=7DI6op61AY)\n\u003cp id=\"2.3.2\"\u003e\u003c/p \u003e\n\n  - Time Series Forecasting\n    - [Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting](http://proceedings.mlr.press/v139/rasul21a.html)\n    - [Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models](https://arxiv.org/abs/2208.09399)\n    - [Retrieval-Augmented Diffusion Models for Time Series Forecasting](https://arxiv.org/abs/2410.18712)\n\u003cp id=\"2.3.3\"\u003e\u003c/p \u003e\n\n  - Waveform Signal Processing\n    - [WaveGrad: Estimating Gradients for Waveform Generation. ](https://openreview.net/forum?id=NsMLjcFaO8O)\n    - [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://openreview.net/forum?id=a-xFK8Ymz5J)  \n\n\n\u003cp id=\"2.4\"\u003e\u003c/p\u003e\n\n### 4. Multi-Modal Learning\n\u003cp id=\"2.4.1\"\u003e\u003c/p \u003e\n\n  - Text-to-Image Generation\n    - [Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n    - [Blended diffusion for text-driven editing of natural images](https://openaccess.thecvf.com/content/CVPR2022/html/Avrahami_Blended_Diffusion_for_Text-Driven_Editing_of_Natural_Images_CVPR_2022_paper.html)\n    - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://arxiv.org/abs/2204.06125)\n    - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://arxiv.org/abs/2205.11487)\n    - [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://arxiv.org/abs/2112.10741)\n    - [Vector quantized diffusion model for text-to-image synthesis. ](https://openaccess.thecvf.com/content/CVPR2022/html/Gu_Vector_Quantized_Diffusion_Model_for_Text-to-Image_Synthesis_CVPR_2022_paper.html)\n    - [Frido: Feature Pyramid Diffusion for Complex Image Synthesis.](https://arxiv.org/abs/2208.13753)\n    - [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://arxiv.org/abs/2208.12242)\n    - [Imagic: Text-Based Real Image Editing with Diffusion Models](https://arxiv.org/abs/2210.09276)\n    - [UniTune: Text-Driven Image Editing by Fine Tuning an Image Generation Model on a Single Image](https://arxiv.org/abs/2210.09477)\n    - [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://openaccess.thecvf.com/content/CVPR2022/html/Kim_DiffusionCLIP_Text-Guided_Diffusion_Models_for_Robust_Image_Manipulation_CVPR_2022_paper.html)\n    - [One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale](https://ml.cs.tsinghua.edu.cn/diffusion/unidiffuser.pdf)\n    - [TextDiffuser: Diffusion Models as Text Painters](https://arxiv.org/abs/2305.10855)\n    - [Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n    - [Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing](https://openreview.net/forum?id=nFMS6wF2xq)\n    - [RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models](https://arxiv.org/abs/2402.12908)\n    - [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://arxiv.org/abs/2401.11708)\n    - [EditWorld: Simulating World Dynamics for Instruction-Following Image Editing](https://arxiv.org/abs/2405.14785)\n    - [IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation](https://arxiv.org/abs/2410.07171)\n    - [Consistency Flow Matching: Defining Straight Flows with Velocity Consistency](https://arxiv.org/abs/2407.02398v1)\n    - [Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow](https://arxiv.org/abs/2410.07303)\n    - [Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening](https://arxiv.org/abs/2502.12146)\n\u003cp id=\"2.4.2\"\u003e\u003c/p \u003e\n\n  - Text-to-3D Generation\n    - [Magic3D: High-Resolution Text-to-3D Content Creation](https://arxiv.org/abs/2211.10440)\n    - [DreamFusion: Text-to-3D using 2D Diffusion](https://arxiv.org/abs/2209.14988)\n    - [Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior](https://arxiv.org/pdf/2303.14184v2.pdf)\n    - [Shap·E: Generating Conditional 3D Implicit Functions](https://arxiv.org/pdf/2305.02463.pdf)\n    - [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://arxiv.org/pdf/2303.13873.pdf)\n    - [Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models](https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Dream3D_Zero-Shot_Text-to-3D_Synthesis_Using_3D_Shape_Prior_and_Text-to-Image_CVPR_2023_paper.pdf)\n    - [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://arxiv.org/pdf/2305.16213.pdf)\n    - [LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes](https://arxiv.org/abs/2311.13384)\n    - [GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models](https://arxiv.org/abs/2310.08529)\n    - [IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts](https://arxiv.org/pdf/2310.05375)\n    - [Semantic Score Distillation Sampling for Compositional Text-to-3D Generation](https://arxiv.org/abs/2410.09009)\n    - [Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis](https://arxiv.org/abs/2410.07155)\n\u003cp id=\"2.4.3\"\u003e\u003c/p \u003e\n\n  - Scene Graph/Layout to Image Generation\n    - [Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training](https://arxiv.org/abs/2211.11138)\n    - [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](http://openaccess.thecvf.com/content/CVPR2023/html/Zheng_LayoutDiffusion_Controllable_Diffusion_Model_for_Layout-to-Image_Generation_CVPR_2023_paper.html)\n    - [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://arxiv.org/abs/2305.13655)\n    - [RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models](https://arxiv.org/abs/2402.12908)\n\u003cp id=\"2.4.4\"\u003e\u003c/p \u003e\n\n  - Text-to-Audio Generation\n    - [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://proceedings.mlr.press/v139/popov21a.html)\n    - [Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data](https://arxiv.org/abs/2205.15370)\n    - [Diffsound: Discrete Diffusion Model for Text-to-sound Generation](https://arxiv.org/abs/2207.09983)\n    - [ItôTTS and ItôWave: Linear Stochastic Differential Equation Is All You Need For Audio Generation](https://ui.adsabs.harvard.edu/abs/2021arXiv210507583W/abstract)\n    - [Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models](https://arxiv.org/abs/2206.02246)\n    - [EdiTTS: Score-based Editing for Controllable Text-to-Speech.](https://arxiv.org/abs/2110.02584)\n    - [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech.](https://arxiv.org/abs/2207.06389)\n    - [Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model](https://arxiv.org/pdf/2304.13731v1.pdf)\n\u003cp id=\"2.4.5\"\u003e\u003c/p \u003e\n  \n  - Text-to-Motion Generation\n    - [Human motion diffusion model](https://arxiv.org/abs/2209.14916)\n    - [Motiondiffuse: Text-driven human motion generation with diffusion model](https://arxiv.org/abs/2208.15001)\n    - [Flame: Free-form language-based motion synthesis \u0026 editing](https://arxiv.org/abs/2209.00349)\n\u003cp id=\"2.4.6\"\u003e\u003c/p \u003e\n  \n  - Text-to-Video Generation/Editting\n    - [Make-a-video: Text-to-video generation without text-video data](https://arxiv.org/abs/2209.14792)\n    - [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://arxiv.org/abs/2212.11565)\n    - [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://arxiv.org/abs/2303.09535)\n    - [Imagen video: High definition video generation with diffusion models](https://arxiv.org/abs/2210.02303)\n    - [Conditional Image-to-Video Generation with Latent Flow Diffusion Models](https://arxiv.org/abs/2303.13744)\n    - [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://arxiv.org/abs/2303.13439)\n    - [Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models](https://arxiv.org/abs/2303.17599)\n    - [Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://arxiv.org/abs/2304.01186)\n    - [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://arxiv.org/abs/2303.13439)\n    - [ControlVideo: Training-free Controllable Text-to-Video Generation](https://arxiv.org/abs/2305.13077)\n    - [MotionDirector: Motion Customization of Text-to-Video Diffusion Models](https://arxiv.org/abs/2310.08465)\n    - [Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing](https://openreview.net/forum?id=nFMS6wF2xq)\n    - [Stable video diffusion: Scaling latent video diffusion models to large datasets](https://arxiv.org/abs/2311.15127)\n    - [I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models](https://arxiv.org/abs/2311.04145)\n    - [Lumiere: A space-time diffusion model for video generation](https://arxiv.org/abs/2401.12945)\n    - [Videocrafter1: Open diffusion models for high-quality video generation](https://arxiv.org/abs/2310.19512)\n    - [VideoTetris: Towards Compositional Text-To-Video Generation](https://arxiv.org/abs/2406.04277)\n\u003cp id=\"2.5\"\u003e\u003c/p\u003e\n\n### 5. Robust Learning\n\u003cp id=\"2.5.1\"\u003e\u003c/p \u003e\n\n  - Data Purification\n    - [Diffusion Models for Adversarial Purification](https://arxiv.org/abs/2205.07460)\n    - [Adversarial purification with score-based generative models](http://proceedings.mlr.press/v139/yoon21a.html)\n    - [Threat Model-Agnostic Adversarial Defense using Diffusion Models](https://arxiv.org/abs/2207.08089)\n    - [Guided Diffusion Model for Adversarial Purification](https://arxiv.org/abs/2205.14969)\n    - [Guided Diffusion Model for Adversarial Purification from Random Noise](https://arxiv.org/abs/2206.10875)\n    - [PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition.](https://arxiv.org/abs/2208.09801)\n\u003cp id=\"2.5.2\"\u003e\u003c/p \u003e  \n\n  - Generating Synthetic Data for Robust Learning\n    - [Generating high fidelity data from low-density regions using diffusion models](https://arxiv.org/abs/2203.17260)\n    - [Don’t Play Favorites: Minority Guidance for Diffusion Models](https://arxiv.org/abs/2301.12334)\n    - [Better diffusion models further improve adversarial training](https://arxiv.org/abs/2302.04638)\n\u003cp id=\"2.6\"\u003e\u003c/p\u003e\n\n### 6. Molecular Graph Modeling\n  - [Torsional Diffusion for Molecular Conformer Generation.](https://openreview.net/forum?id=D9IxPlXPJJS)\n  - [Equivariant Diffusion for Molecule Generation in 3D](https://proceedings.mlr.press/v162/hoogeboom22a.html)\n  - [Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2205.15019)\n  - [GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation](https://openreview.net/forum?id=PzcvxEMzvQC)\n  - [Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem](https://arxiv.org/abs/2206.04119)\n  - [Diffusion-based Molecule Generation with Informative Prior Bridge](https://arxiv.org/abs/2209.00865)\n  - [Learning gradient fields for molecular conformation generation](http://proceedings.mlr.press/v139/shi21b.html)\n  - [Predicting molecular conformation via dynamic graph score matching. ](https://proceedings.neurips.cc/paper/2021/hash/a45a1d12ee0fb7f1f872ab91da18f899-Abstract.html)\n  - [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://arxiv.org/abs/2210.01776)\n  - [3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction](https://arxiv.org/abs/2303.03543)\n  - [Learning Joint 2D \u0026 3D Diffusion Models for Complete Molecule Generation](https://arxiv.org/abs/2305.12347)\n  - [Graphusion: Latent Diffusion for Graph Generation](https://ieeexplore.ieee.org/abstract/document/10508504)\n  - [Binding-Adaptive Diffusion Models for Structure-Based Drug Design](https://arxiv.org/abs/2402.18583)\n  - [Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models](https://openreview.net/forum?id=qH9nrMNTIW)\n  - [Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation](https://openreview.net/forum?id=eejhD9FCP3)\n\u003cp id=\"2.7\"\u003e\u003c/p\u003e\n\n### 7. Material Design\n  - [Crystal Diffusion Variational Autoencoder for Periodic Material Generation](https://arxiv.org/abs/2110.06197)\n  - [Antigen-specific antibody design and optimization with diffusion-based generative models](https://www.biorxiv.org/content/10.1101/2022.07.10.499510v1)\n\u003cp id=\"2.8\"\u003e\u003c/p\u003e\n\n### 8. Medical Image Reconstruction\n  - [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://openreview.net/forum?id=vaRCHVj0uGI)\n  - [MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion](https://arxiv.org/abs/2203.12621)\n  - [Score-based diffusion models for accelerated MRI](https://arxiv.org/abs/2110.05243)\n  - [Towards performant and reliable undersampled MR reconstruction via diffusion model sampling](https://arxiv.org/pdf/2203.04292.pdf)\n  - [Come-closer-diffuse-faster: Accelerating conditional diffusion models for inverse problems through stochastic contraction](https://openaccess.thecvf.com/content/CVPR2022/papers/Chung_Come-Closer-Diffuse-Faster_Accelerating_Conditional_Diffusion_Models_for_Inverse_Problems_Through_Stochastic_CVPR_2022_paper.pdf)\n\n\n\n\u003cp id=\"3\"\u003e\u003c/p\u003e\n\n## Connections with Other Generative Models\n\u003cp id=\"3.1\"\u003e\u003c/p\u003e\n\n### 1. Variational Autoencoder\n- [Understanding Diffusion Models: A Unified Perspective](https://arxiv.org/abs/2208.11970)\n- [A variational perspective on diffusion-based generative models and score matching](https://proceedings.neurips.cc/paper/2021/hash/c11abfd29e4d9b4d4b566b01114d8486-Abstract.html)\n- [Score-based generative modeling in latent space](https://proceedings.neurips.cc/paper/2021/hash/5dca4c6b9e244d24a30b4c45601d9720-Abstract.html)\n- [Improving Diffusion-Based Image Synthesis with Context Prediction](https://openreview.net/forum?id=wRhLd65bDt)\n\u003cp id=\"3.2\"\u003e\u003c/p\u003e\n\n### 2. Generative Adversarial Network\n  - [Diffusion-GAN: Training GANs with Diffusion. ](https://arxiv.org/abs/2206.02262)\n  - [Tackling the generative learning trilemma with denoising diffusion gans](https://openreview.net/forum?id=JprM0p-q0Co)\n  - [Structure-Guided Adversarial Training of Diffusion Models](https://arxiv.org/abs/2402.17563)\n\u003cp id=\"3.3\"\u003e\u003c/p\u003e\n\n### 3. Normalizing Flow\n  - [Diffusion Normalizing Flow](https://proceedings.neurips.cc/paper/2021/hash/876f1f9954de0aa402d91bb988d12cd4-Abstract.html)\n  - [Interpreting diffusion score matching using normalizing flow](https://openreview.net/forum?id=jxsmOXCDv9l)\n  - [Maximum Likelihood Training of Implicit Nonlinear Diffusion Models](https://openreview.net/forum?id=TQn44YPuOR2)\n  - [Consistency Flow Matching: Defining Straight Flows with Velocity Consistency](https://arxiv.org/abs/2407.02398v1)\n  - [Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow](https://arxiv.org/abs/2410.07303)\n\u003cp id=\"3.4\"\u003e\u003c/p\u003e\n\n### 4. Autoregressive Models\n  - [Autoregressive Diffusion Models. ](https://openreview.net/forum?id=Lm8T39vLDTE)\n  - [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting. ](http://proceedings.mlr.press/v139/rasul21a.html)\n\u003cp id=\"3.5\"\u003e\u003c/p\u003e\n\n### 5. Energy-Based Models\n  - [Learning Energy-Based Models by Diffusion Recovery Likelihood](https://openreview.net/forum?id=v_1Soh8QUNc)\n  - [Latent Diffusion Energy-Based Model for Interpretable Text Modeling](https://proceedings.mlr.press/v162/yu22h.html)\n## Citing\nIf you find this work useful, please cite our paper:\n```\n@article{yang2023diffusurvey,\n  title={Diffusion models: A comprehensive survey of methods and applications},\n  author={Yang, Ling and Zhang, Zhilong and Song, Yang and Hong, Shenda and Xu, Runsheng and Zhao, Yue and Zhang, Wentao and Cui, Bin and Yang, Ming-Hsuan},\n  journal={ACM Computing Surveys},\n  volume={56},\n  number={4},\n  pages={1--39},\n  year={2023},\n  publisher={ACM New York, NY, USA}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyangling0818%2Fdiffusion-models-papers-survey-taxonomy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyangling0818%2Fdiffusion-models-papers-survey-taxonomy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyangling0818%2Fdiffusion-models-papers-survey-taxonomy/lists"}