{"id":4671,"url":"https://github.com/diff-usion/Awesome-Diffusion-Models","name":"Awesome-Diffusion-Models","description":" A collection of resources and papers on Diffusion Models","projects_count":2974,"last_synced_at":"2026-05-30T20:00:23.922Z","repository":{"id":37099901,"uuid":"407722319","full_name":"diff-usion/Awesome-Diffusion-Models","owner":"diff-usion","description":" A collection of resources and papers on Diffusion Models","archived":false,"fork":false,"pushed_at":"2024-08-01T07:11:20.000Z","size":1925,"stargazers_count":12321,"open_issues_count":27,"forks_count":1012,"subscribers_count":265,"default_branch":"main","last_synced_at":"2026-05-14T07:03:21.457Z","etag":null,"topics":["artificial-intelligence","diffusion-models","generative-model","machine-learning","score-based","score-matching"],"latest_commit_sha":null,"homepage":"https://diff-usion.github.io/Awesome-Diffusion-Models/","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/diff-usion.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"license","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}},"created_at":"2021-09-18T01:24:24.000Z","updated_at":"2026-05-13T14:44:15.000Z","dependencies_parsed_at":"2023-07-13T02:38:32.762Z","dependency_job_id":"65828d2d-f2ba-4eff-9554-a4f39dbd8cd7","html_url":"https://github.com/diff-usion/Awesome-Diffusion-Models","commit_stats":{"total_commits":210,"total_committers":21,"mean_commits":10.0,"dds":0.5857142857142856,"last_synced_commit":"01be334d2e258b0150093761d77ab55b789e88d3"},"previous_names":["heejkoo/awesome-diffusion-models","diff-usion/awesome-diffusion-models"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/diff-usion/Awesome-Diffusion-Models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diff-usion%2FAwesome-Diffusion-Models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diff-usion%2FAwesome-Diffusion-Models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diff-usion%2FAwesome-Diffusion-Models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diff-usion%2FAwesome-Diffusion-Models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/diff-usion","download_url":"https://codeload.github.com/diff-usion/Awesome-Diffusion-Models/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diff-usion%2FAwesome-Diffusion-Models/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33707328,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-30T02:00:06.278Z","response_time":92,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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"}},"created_at":"2024-01-06T20:25:01.313Z","updated_at":"2026-05-30T20:00:23.922Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Vision","Reinforcement Learning","Survey","Introductory Posts","Introductory Papers","Introductory Videos","Introductory Lectures","Tutorial and Jupyter Notebook","Natural Language","Tabular and Time Series","Graph","Audio","Applications","Theory"],"sub_categories":["Inverse Problems","Multi-modal Learning","Molecular and Material Generation","Generation","Segmentation","Classification","3D Vision","Adversarial Attack","Image Translation","Miscellany","Text-to-Speech","Medical Imaging","Separation","Forecasting","Conversion","Enhancement","Imputation"],"readme":"[![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/hee9joon/Awesome-Diffusion-Models) \n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)\n[![Made With Love](https://img.shields.io/badge/Made%20With-Love-red.svg)](https://github.com/chetanraj/awesome-github-badges)\n\nThis repository contains a collection of resources and papers on ***Diffusion Models***.\n\nPlease refer to [this page](https://diff-usion.github.io/Awesome-Diffusion-Models/) as this page may not contain all the information due to page constraints.\n\n## Contents\n- [Resources](#resources)\n  - [Introductory Posts](#introductory-posts)\n  - [Introductory Papers](#introductory-papers)\n  - [Introductory Videos](#introductory-videos)\n  - [Introductory Lectures](#introductory-lectures)\n  - [Tutorial and Jupyter Notebook](#tutorial-and-jupyter-notebook)\n- [Papers](#papers)\n  - [Survey](#survey)\n  - [Vision](#vision)\n    - [Generation](#generation)\n    - [Classification](#classification)\n    - [Segmentation](#segmentation)\n    - [Image Translation](#image-translation)\n    - [Inverse Problems](#inverse-problems)\n    - [Medical Imaging](#medical-imaging)\n    - [Multi-modal Learning](#multi-modal-learning)\n    - [3D Vision](#3d-vision)\n    - [Adversarial Attack](#adversarial-attack)\n    - [Miscellany](#miscellany)\n  - [Audio](#audio)\n    - [Generation](#generation-1)\n    - [Conversion](#conversion)\n    - [Enhancement](#enhancement)\n    - [Separation](#separation)\n    - [Text-to-Speech](#text-to-speech)\n    - [Miscellany](#miscellany-1)\n  - [Natural Language](#natural-language)\n  - [Tabular and Time Series](#tabular-and-time-series)\n    - [Generation](#generation-2)\n    - [Forecasting](#forecasting)\n    - [Imputation](#imputation)\n    - [Miscellany](#miscellany-2)\n  - [Graph](#graph)\n    - [Generation](#generation-3)\n    - [Molecular and Material Generation](#molecular-and-material-generation)\n  - [Reinforcement Learning](#reinforcement-learning)\n  - [Theory](#theory)\n  - [Applications](#applications)\n\n\n# Resources\n## Introductory Posts\n\n**:fast_forward: DiffusionFastForward: 01-Diffusion-Theory** \\\n*Mikolaj Czerkawski (@mikonvergence)* \\\n[[Website](https://github.com/mikonvergence/DiffusionFastForward/blob/master/notes/01-Diffusion-Theory.md)] \\\n4 Feb 2023\n\n**How diffusion models work: the math from scratch** \\\n*Sergios Karagiannakos,Nikolas Adaloglou* \\\n[[Website](https://theaisummer.com/diffusion-models/?fbclid=IwAR1BIeNHqa3NtC8SL0sKXHATHklJYphNH-8IGNoO3xZhSKM_GYcvrrQgB0o)] \\\n24 Sep 2022\n\n**A Path to the Variational Diffusion Loss** \\\n*Alex Alemi* \\\n[[Website](https://blog.alexalemi.com/diffusion.html)] [[Colab](https://colab.research.google.com/github/google-research/vdm/blob/main/colab/SimpleDiffusionColab.ipynb)] \\\n15 Sep 2022\n\n**The Annotated Diffusion Model** \\\n*Niels Rogge, Kashif Rasul* \\\n[[Website](https://huggingface.co/blog/annotated-diffusion)] \\\n06 Jun 2022\n\n**The recent rise of diffusion-based models** \\\n*Maciej Domagała* \\\n[[Website](https://maciejdomagala.github.io/generative_models/2022/06/06/The-recent-rise-of-diffusion-based-models.html)] \\\n06 Jun 2022\n\n**Introduction to Diffusion Models for Machine Learning** \\\n*Ryan O'Connor* \\\n[[Website](https://www.assemblyai.com/blog/diffusion-models-for-machine-learning-introduction/)] \\\n12 May 2022\n\n**Improving Diffusion Models as an Alternative To GANs** \\\n*Arash Vahdat and Karsten Kreis* \\\n[[Website-Part 1](https://developer.nvidia.com/blog/improving-diffusion-models-as-an-alternative-to-gans-part-1/)] [[Website-Part 2](https://developer.nvidia.com/blog/improving-diffusion-models-as-an-alternative-to-gans-part-2/)] \\\n26 Apr 2022\n\n**An introduction to Diffusion Probabilistic Models** \\\n*Ayan Das* \\\n[[Website](https://ayandas.me/blog-tut/2021/12/04/diffusion-prob-models.html)] \\\n04 Dec 2021\n\n**Introduction to deep generative modeling: Diffusion-based Deep Generative Models** \\\n*Jakub Tomczak* \\\n[[Website](https://jmtomczak.github.io/blog/10/10_ddgms_lvm_p2.html)] \\\n30 Aug 2021\n\n**What are Diffusion Models?** \\\n*Lilian Weng* \\\n[[Website](https://lilianweng.github.io/lil-log/2021/07/11/diffusion-models.html)] \\\n11 Jul 2021\n\n**Diffusion Models as a kind of VAE** \\\n*Angus Turner* \\\n[[Website](https://angusturner.github.io/generative_models/2021/06/29/diffusion-probabilistic-models-I.html)] \\\n29 Jun 2021\n\n**Generative Modeling by Estimating Gradients of the Data Distribution** \\\n*Yang Song* \\\n[[Website](https://yang-song.github.io/blog/2021/score/)] \\\n5 May 2021\n\n## Introductory Papers\n\n**Understanding Diffusion Models: A Unified Perspective** \\\n*Calvin Luo* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.11970)] \\\n25 Aug 2022\n\n**How to Train Your Energy-Based Models** \\\n*Yang Song, Diederik P. Kingma* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2101.03288)] \\\n9 Jan 2021\n\n## Introductory Videos\n\n**:fast_forward: DiffusionFastForward** \\\n*Mikolaj Czerkawski (@mikonvergence)* \\\n[[Video](https://www.youtube.com/playlist?list=PL5RHjmn-MVHDMcqx-SI53mB7sFOqPK6gN)] \\\n4 Mar 2023\n\n**Diffusion models from scratch in PyTorch** \\\n*DeepFindr* \\\n[[Video](https://www.youtube.com/watch?v=a4Yfz2FxXiY)] \\\n18 Jul 2022\n\n**Diffusion Models | Paper Explanation | Math Explained** \\\n*Outlier* \\\n[[Video](https://www.youtube.com/watch?v=HoKDTa5jHvg)] \\\n6 Jun 2022\n\n**What are Diffusion Models?** \\\n*Ari Seff* \\\n[[Video](https://www.youtube.com/watch?v=fbLgFrlTnGU\u0026list=LL\u0026index=2)] \\\n20 Apr 2022\n\n**Diffusion models explained** \\\n*AI Coffee Break with Letitia* \\\n[[Video](https://www.youtube.com/watch?v=344w5h24-h8\u0026ab_channel=AICoffeeBreakwithLetitia)] \\\n23 Mar 2022\n\n## Introductory Lectures\n\n**Denoising Diffusion-based Generative Modeling: Foundations and Applications** \\\n*Karsten Kreis, Ruiqi Gao, Arash Vahdat* \\\n[[Page](https://cvpr2022-tutorial-diffusion-models.github.io/)] \\\n19 Jun 2022\n\n**Diffusion Probabilistic Models** \\\n*Jascha Sohl-Dickstein, MIT 6.S192 - Lecture 22* \\\n[[Video](https://www.youtube.com/watch?v=XCUlnHP1TNM)] \\\n19 Apr 2022\n\n## Tutorial and Jupyter Notebook\n\n**:fast_forward: DiffusionFastForward: train from scratch in colab** \\\n*Mikolaj Czerkawski (@mikonvergence)* \\\n[[Github](https://github.com/mikonvergence/DiffusionFastForward)]\n[[notebook](https://github.com/mikonvergence/DiffusionFastForward#computer-code)]\n\n**diffusion-for-beginners** \\\n*ozanciga* \\\n[[Github](https://github.com/ozanciga/diffusion-for-beginners)]\n\n**Beyond Diffusion: What is Personalized Image Generation and How Can You Customize Image Synthesis?** \\\n*J. Rafid Siddiqui* \\\n[[Github](https://github.com/azad-academy/personalized-diffusion)] [[Medium](https://medium.com/mlearning-ai/beyond-diffusion-what-is-personalized-image-generation-and-how-can-you-customize-image-synthesis-26a89d5b335)]\n\n**Diffusion_models_tutorial** \\\n*FilippoMB* \\\n[[Github](https://github.com/FilippoMB/Diffusion_models_tutorial)]\n\n**ScoreDiffusionModel** \\\n*JeongJiHeon* \\\n[[Github](https://github.com/JeongJiHeon/ScoreDiffusionModel)]\n\n**Minimal implementation of diffusion models** \\\n*VSehwag* \\\n[[Github](https://github.com/VSehwag/minimal-diffusion)]\n\n**diffusion_tutorial** \\\n*sunlin-ai* \\\n[[Github](https://github.com/sunlin-ai/diffusion_tutorial)] \n\n**Denoising diffusion probabilistic models** \\\n*acids-ircam* \\\n[[Github](https://github.com/acids-ircam/diffusion_models)] \n\n\n**Centipede Diffusion** \\\n*Zalring* \\\n[[Notebook](https://colab.research.google.com/github/Zalring/Centipede_Diffusion/blob/main/Centipede_Diffusion.ipynb)]\n\n**Deforum Stable Diffusion** \\\n*deforum* \\\n[[Notebook](https://colab.research.google.com/github/deforum/stable-diffusion/blob/main/Deforum_Stable_Diffusion.ipynb)]\n\n**Stable Diffusion Interpolation** \\\n*None* \\\n[[Notebook](https://colab.research.google.com/drive/1EHZtFjQoRr-bns1It5mTcOVyZzZD9bBc?usp=sharing)]\n\n**Keras Stable Diffusion: GPU starter example** \\\n*None* \\\n[[Notebook](https://colab.research.google.com/drive/1zVTa4mLeM_w44WaFwl7utTaa6JcaH1zK)]\n\n**Huemin Jax Diffusion** \\\n*huemin-art* \\\n[[Notebook](https://colab.research.google.com/github/huemin-art/jax-guided-diffusion/blob/v2.7/Huemin_Jax_Diffusion_2_7.ipynb)]\n\n**Disco Diffusion** \\\n*alembics* \\\n[[Notebook](https://colab.research.google.com/github/alembics/disco-diffusion/blob/main/Disco_Diffusion.ipynb)]\n\n**Simplified Disco Diffusion** \\\n*entmike* \\\n[[Notebook](https://colab.research.google.com/github/entmike/disco-diffusion-1/blob/main/Simplified_Disco_Diffusion.ipynb)]\n\n**WAS's Disco Diffusion - Portrait Generator Playground** \\\n*WASasquatch* \\\n[[Notebook](https://colab.research.google.com/github/WASasquatch/disco-diffusion-portrait-playground/blob/main/WAS's_Disco_Diffusion_v5_6_9_%5BPortrait_Generator_Playground%5D.ipynb)]\n\n**Diffusers - Hugging Face** \\\n*huggingface* \\\n[[Notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb)] \n\n\n# Papers\n\n## Survey\n\n**A Survey on Video Diffusion Models** \\\n*Zhen Xing, Qijun Feng, Haoran Chen, Qi Dai, Han Hu, Hang Xu, Zuxuan Wu and Yu-Gang Jiang*\narXiv 2023. [[Paper](https://arxiv.org/pdf/2310.10647.pdf)] \\\n16 Oct 2023\n\n**State of the Art on Diffusion Models for Visual Computing** \\\n*Ryan Po, Wang Yifan, Vladislav Golyanik, Kfir Aberman, Jonathan T. Barron, Amit H. Bermano, Eric Ryan Chan, Tali Dekel, Aleksander Holynski, Angjoo Kanazawa, C. Karen Liu, Lingjie Liu, Ben Mildenhall, Matthias Nießner, Björn Ommer, Christian Theobalt, Peter Wonka, Gordon Wetzstein* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.07204)] \\\n11 Oct 2023\n\n**Memory in Plain Sight: A Survey of the Uncanny Resemblances between Diffusion Models and Associative Memories** \\\n*Benjamin Hoover, Hendrik Strobelt, Dmitry Krotov, Judy Hoffman, Zsolt Kira, Duen Horng Chau* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.16750)] \\\n28 Sep 2023\n\n**A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions** \\\n*Tianyi Zhang, Zheng Wang, Jing Huang, Mohiuddin Muhammad Tasnim, Wei Shi* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.13142)] \\\n25 Aug 2023\n\n**Diffusion Models for Image Restoration and Enhancement -- A Comprehensive Survey** \\\n*Xin Li, Yulin Ren, Xin Jin, Cuiling Lan, Xingrui Wang, Wenjun Zeng, Xinchao Wang, Zhibo Chen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.09388)] \\\n18 Aug 2023\n\n**A Comprehensive Survey on Generative Diffusion Models for Structured Data** \\\n*Heejoon Koo, To Eun Kim* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.04139)] \\\n7 Jun 2023\n\n**On the Design Fundamentals of Diffusion Models: A Survey** \\\n*Ziyi Chang, George A. Koulieris, Hubert P. H. Shum* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.04542)] \\\n7 Jun 2023\n\n**Diffusion Models in NLP: A Survey** \\\n*Hao Zou, Zae Myung Kim, Dongyeop Kang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.14671)] \\\n24 May 2023\n\n**Diffusion Models for Time Series Applications: A Survey** \\\n*Lequan Lin, Zhengkun Li, Ruikun Li, Xuliang Li, Junbin Gao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.00624)] \\\n1 May 2023\n\n**A Comprehensive Survey on Knowledge Distillation of Diffusion Models** \\\n*Weijian Luo* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.04262)] \\\n9 Apr 2023\n\n**A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Material** \\\n*Mengchun Zhang, Maryam Qamar, Taegoo Kang, Yuna Jung, Chenshuang Zhang, Sung-Ho Bae, Chaoning Zhang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.01565)] \\\n4 Apr 2023\n\n**Audio Diffusion Model for Speech Synthesis: A Survey on Text To Speech and Speech Enhancement in Generative AI** \\\n*Chenshuang Zhang, Chaoning Zhang, Sheng Zheng, Mengchun Zhang, Maryam Qamar, Sung-Ho Bae, In So Kweon* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.13336)] \\\n23 Mar 2023\n\n**Diffusion Models in NLP: A Survey** \\\n*Yuansong Zhu, Yu Zhao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.07576)] \\\n14 Mar 2023\n\n**Text-to-image Diffusion Model in Generative AI: A Survey** \\\n*Chenshuang Zhang, Chaoning Zhang, Mengchun Zhang, In So Kweon* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.07909)] \\\n14 Mar 2023\n\n**Diffusion Models for Non-autoregressive Text Generation: A Survey** \\\n*Yifan Li, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.06574)] \\\n12 Mar 2023\n\n**Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Action** \\\n*Zhiye Guo, Jian Liu, Yanli Wang, Mengrui Chen, Duolin Wang, Dong Xu, Jianlin Cheng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.10907)] \\\n13 Feb 2023\n\n**Generative Diffusion Models on Graphs: Methods and Applications** \\\n*Wenqi Fan, Chengyi Liu, Yunqing Liu, Jiatong Li, Hang Li, Hui Liu, Jiliang Tang, Qing Li* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.02591)] \\\n6 Feb 2023\n\n**Diffusion Models for Medical Image Analysis: A Comprehensive Survey** \\\n*Amirhossein Kazerouni, Ehsan Khodapanah Aghdam, Moein Heidari, Reza Azad, Mohsen Fayyaz, Ilker Hacihaliloglu, Dorit Merhof* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.07804)] [[Github](https://github.com/amirhossein-kz/Awesome-Diffusion-Models-in-Medical-Imaging)] \\\n14 Nov 2022\n\n**Efficient Diffusion Models for Vision: A Survey** \\\n*Anwaar Ulhaq, Naveed Akhtar, Ganna Pogrebna* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.09292)] \\\n7 Oct 2022\n\n**Diffusion Models in Vision: A Survey** \\\n*Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Mubarak Shah* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.04747)] \\\n10 Sep 2022\n\n**A Survey on Generative Diffusion Model** \\\n*Hanqun Cao, Cheng Tan, Zhangyang Gao, Guangyong Chen, Pheng-Ann Heng, Stan Z. Li* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.02646)] \\\n6 Sep 2022\n\n**Diffusion Models: A Comprehensive Survey of Methods and Applications** \\\n*Ling Yang, Zhilong Zhang, Shenda Hong, Wentao Zhang* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.00796)] \\\n2 Sep 2022\n\n## Vision\n### Generation\n\n**DiffEnc: Variational Diffusion with a Learned Encoder** \\\n*Beatrix M. G. Nielsen, Anders Christensen, Andrea Dittadi, Ole Winther* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.19789)] \\\n30 Oct 2023\n\n**Upgrading VAE Training With Unlimited Data Plans Provided by Diffusion Models** \\\n*Tim Z. Xiao, Johannes Zenn, Robert Bamler* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.19653)] \\\n30 Oct 2023\n\n**Successfully Applying Lottery Ticket Hypothesis to Diffusion Model** \\\n*Chao Jiang, Bo Hui, Bohan Liu, Da Yan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.18823)] \\\n28 Oct 2023\n\n**Noise-Free Score Distillation** \\\n*Oren Katzir, Or Patashnik, Daniel Cohen-Or, Dani Lischinski* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.17590)] \\\n26 Oct 2023\n\n**The statistical thermodynamics of generative diffusion models** \\\n*Luca Ambrogioni* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.17467)] \\\n26 Oct 2023\n\n**Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise** \\\n*Zhenkai Zhang, Krista A. Ehinger, Tom Drummond* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.17167)] \\\n26 Oct 2023\n\n**Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration** \\\n*Longlin Yu, Tianyu Xie, Yu Zhu, Tong Yang, Xiangyu Zhang, Cheng Zhang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.17153)] [[Github](https://github.com/longinyu/hsivi)] \\\n26 Oct 2023\n\n**RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesis** \\\n*Anant Khandelwal* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.16074)] \\\n24 Oct 2023\n\n**Improved Techniques for Training Consistency Models** \\\n*Yang Song, Prafulla Dhariwal* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.14189)] \\\n22 Oct 2023\n\n**ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection** \\\n*Zhongzhan Huang, Pan Zhou, Shuicheng Yan, Liang Lin* \\\nNeurIPS 2023. [[Paper](https://arxiv.org/abs/2310.13545)] [[Github](https://github.com/sail-sg/ScaleLong)] \\\n20 Oct 2023\n\n\n**Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models** \\\n*Gabriele Corso, Yilun Xu, Valentin de Bortoli, Regina Barzilay, Tommi Jaakkola* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.13102)] [[Github](https://github.com/gcorso/particle-guidance)] \\\n19 Oct 2023\n\n**Closed-Form Diffusion Models** \\\n*Christopher Scarvelis, Haitz Sáez de Ocáriz Borde, Justin Solomon* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.12395)] \\\n19 Oct 2023\n\n**Elucidating The Design Space of Classifier-Guided Diffusion Generation** \\\n*Jiajun Ma, Tianyang Hu, Wenjia Wang, Jiacheng Sun* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.11311)] [[Github](https://github.com/alexmaols/elucd)] \\\n17 Oct 2023\n\n\n**BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference** \\\n*Siqi Kou, Lei Gan, Dequan Wang, Chongxuan Li, Zhijie Deng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.11142)] \\\n17 Oct 2023\n\n**Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models** \\\n*Zijian Zhang, Luping Liu. Zhijie Lin, Yichen Zhu, Zhou Zhao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.09912)] \\\n15 Oct 2023\n\n**Towards More Accurate Diffusion Model Acceleration with A Timestep Aligner** \\\n*Mengfei Xia, Yujun Shen, Changsong Lei, Yu Zhou, Ran Yi, Deli Zhao, Wenping Wang, Yong-jin Liu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.09469)] \\\n14 Oct 2023\n\n**Unseen Image Synthesis with Diffusion Models** \\\n*Ye Zhu, Yu Wu, Zhiwei Deng, Olga Russakovsky, Yan Yan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.09213)] \\\n13 Oct 2023\n\n**Debias the Training of Diffusion Models** \\\n*Hu Yu, Li Shen, Jie Huang, Man Zhou, Hongsheng Li, Feng Zhao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.08442)] \\\n12 Oct 2023\n\n**Neural Diffusion Models** \\\n*Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.08337)] \\\n12 Oct 2023\n\n**Efficient Integrators for Diffusion Generative Models** \\\n*Kushagra Pandey, Maja Rudolph, Stephan Mandt* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.07894)] \\\n11 Oct 2023\n\n\n**Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling** \\\n*Huangjie Zheng, Zhendong Wang, Jianbo Yuan, Guanghan Ning, Pengcheng He, Quanzeng You, Hongxia Yang, Mingyuan Zhou* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.06389)] \\\n10 Oct 2023\n\n**Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation** \\\n*Lijun Yu, José Lezama, Nitesh B. Gundavarapu, Luca Versari, Kihyuk Sohn, David Minnen, Yong Cheng, Agrim Gupta, Xiuye Gu, Alexander G. Hauptmann, Boqing Gong, Ming-Hsuan Yang, Irfan Essa, David A. Ross, Lu Jiang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.05737)] [[Github](https://github.com/lucidrains/magvit2-pytorch)] \\\n9 Oct 2023\n\n**The Emergence of Reproducibility and Consistency in Diffusion Models** \\\n*Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Liyue Shen, Qing Qu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.05264)] \\\n8 Oct 2023\n\n**DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures** \\\n*Wenhao Li, Xiu Su, Shan You, Fei Wang, Chen Qian, Chang Xu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.04750)] \\\n7 Oct 2023\n\n**Observation-Guided Diffusion Probabilistic Models** \\\n*Junoh Kang, Jinyoung Choi, Sungik Choi, Bohyung Han* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.04041)] \\\n6 Oct 2023\n\n**Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference** \\\n*Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, Hang Zhao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.04378)] \\\n6 Oct 2023\n\n**Denoising Diffusion Step-aware Models** \\\n*Shuai Yang, Yukang Chen, Luozhou Wang, Shu Liu, Yingcong Chen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.03337)] \\\n5 Oct 2023\n\n\n**EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models** \\\n*Yefei He, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.03270)] \\\n5 Oct 2023\n\n**Learning Energy-Based Prior Model with Diffusion-Amortized MCMC** \\\n*Peiyu Yu, Yaxuan Zhu, Sirui Xie, Xiaojian Ma, Ruiqi Gao, Song-Chun Zhu, Ying Nian Wu* \\\nNeurIPS 2023. [[Paper](https://arxiv.org/abs/2310.03218)] [[Github](https://github.com/yuPeiyu98/Diffusion-Amortized-MCMC)] \\\n5 Oct 2023\n\n**On Memorization in Diffusion Models** \\\n*Xiangming Gu, Chao Du, Tianyu Pang, Chongxuan Li, Min Lin, Ye Wang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.02664)] [[Github](https://github.com/sail-sg/DiffMemorize)] \\\n4 Oct 2023\n\n\n**Sequential Data Generation with Groupwise Diffusion Process** \\\n*Sangyun Lee, Gayoung Lee, Hyunsu Kim, Junho Kim, Youngjung Uh* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.01400)] \\\n2 Oct 2023\n\n**Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion** \\\n*Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, Stefano Ermon* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.02279)] \\\n1 Oct 2023\n\n**Completing Visual Objects via Bridging Generation and Segmentation** \\\n*Xiang Li, Yinpeng Chen, Chung-Ching Lin, Rita Singh, Bhiksha Raj, Zicheng Liu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.00808)] \\\n1 Oct 2023\n\n**Decoding Realistic Images from Brain Activity with Contrastive Self-supervision and Latent Diffusion** \\\n*Jingyuan Sun, Mingxiao Li, Marie-Francine Moens* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.00318)] \\\n30 Sep 2023\n\n**FashionFlow: Leveraging Diffusion Models for Dynamic Fashion Video Synthesis from Static Imagery** \\\n*Tasin Islam, Alina Miron, XiaoHui Liu, Yongmin Li* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.00106)] \\\n29 Sep 2023\n\n**Denoising Diffusion Bridge Models** \\\n*Linqi Zhou, Aaron Lou, Samar Khanna, Stefano Ermon* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.16948)] \\\n29 Sep 2023\n\n\n**DeeDiff: Dynamic Uncertainty-Aware Early Exiting for Accelerating Diffusion Model Generation** \\\n*Shengkun Tang, Yaqing Wang, Caiwen Ding, Yi Liang, Yao Li, Dongkuan Xu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.17074)] \\\n29 Sep 2023\n\n\n**Distilling ODE Solvers of Diffusion Models into Smaller Steps** \\\n*Sanghwan Kim, Hao Tang, Fisher Yu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.16421)] \\\n28 Sep 2023\n\n**Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation** \\\n*Xin Yuan, Michael Maire* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.15726)] \\\n27 Sep 2023\n\n**Generative Escher Meshes** \\\n*Noam Aigerman, Thibault Groueix* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.14564)] \\\n25 Sep 2023\n\n**Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models** \\\n*Yangming Li, Boris van Breugel, Mihaela van der Schaar* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.14068)] \\\n25 Sep 2023\n\n**GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER** \\\n*Mingzhen Sun, Weining Wang, Zihan Qin, Jiahui Sun, Sihan Chen, Jing Liu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.13274)] [[Github](https://github.com/iva-mzsun/glober)] \\\n23 Sep 2023\n\n**Score Mismatching for Generative Modeling** \\\n*Senmao Ye, Fei Liu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.11043)] \\\n20 Sep 2023\n\n**Generalised Probabilistic Diffusion Scale-Spaces** \\\n*Pascal Peter* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.08511)] \\\n15 Sep 2023\n\n**Generative Image Dynamics** \\\n*Zhengqi Li, Richard Tucker, Noah Snavely, Aleksander Holynski* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.07906)] [[Project](https://generative-dynamics.github.io/)] \\\n14 Sep 2023\n\n**Beta Diffusion** \\\n*Mingyuan Zhou, Tianqi Chen, Zhendong Wang, Huangjie Zheng* \\\nNeurIPS 2023. [[Paper](https://arxiv.org/abs/2309.07867)] \\\n14 Sep 2023\n\n**Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models** \\\n*Zalan Fabian, Berk Tinaz, Mahdi Soltanolkotabi* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.06642)] \\\n12 Sep 2023\n\n**Elucidating the solution space of extended reverse-time SDE for diffusion models** \\\n*Qinpeng Cui, Xinyi Zhang, Zongqing Lu, Qingmin Liao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.06169)] \\\n12 Sep 2023\n\n\n**Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood** \\\n*Yaxuan Zhu, Jianwen Xie, Yingnian Wu, Ruiqi Gao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.05153)] \\\n10 Sep 2023\n\n**Relay Diffusion: Unifying diffusion process across resolutions for image synthesis** \\\n*Jiayan Teng, Wendi Zheng, Ming Ding, Wenyi Hong, Jianqiao Wangni, Zhuoyi Yang, Jie Tang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.03350)] \\\n4 Sep 2023\n\n**Gradient Domain Diffusion Models for Image Synthesis** \\\n*Yuanhao Gong* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.01875)] \\\n5 Sep 2023\n\n\n**Hierarchical Masked 3D Diffusion Model for Video Outpainting** \\\n*Fanda Fan, Chaoxu Guo, Litong Gong, Biao Wang, Tiezheng Ge, Yuning Jiang, Chunjie Luo, Jianfeng Zhan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.02119)] [[Github](https://fanfanda.github.io/M3DDM/)] \\\n5 Sep 2023\n\n**Diffusion Models with Deterministic Normalizing Flow Priors** \\\n*Mohsen Zand, Ali Etemad, Michael Greenspan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2309.01274)] [[Github](https://github.com/MohsenZand/DiNof)] \\\n3 Sep 2023\n\n**Diffusion Inertial Poser: Human Motion Reconstruction from Arbitrary Sparse IMU Configurations** \\\n*Tom Van Wouwe, Seunghwan Lee, Antoine Falisse, Scott Delp, C. Karen Liu* \\\nAAAI 2024. [[Paper](https://arxiv.org/abs/2308.16682)] \\\n31 Aug 2023\n\n**Conditioning Score-Based Generative Models by Neuro-Symbolic Constraints** \\\n*Davide Scassola, Sebastiano Saccani, Ginevra Carbone, Luca Bortolussi* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.16534)] \\\n31 Aug 2023\n\n**Elucidating the Exposure Bias in Diffusion Models** \\\n*Mang Ning, Mingxiao Li, Jianlin Su, Albert Ali Salah, Itir Onal Ertugrul* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.15321)] \\\n29 Aug 2023\n\n**Residual Denoising Diffusion Models** \\\n*Jiawei Liu, Qiang Wang, Huijie Fan, Yinong Wang, Yandong Tang, Liangqiong Qu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.13712)] [[Github](https://github.com/nachifur/RDDM)] \\\n25 Aug 2023\n\n**Efficient Transfer Learning in Diffusion Models via Adversarial Noise** \\\n*Xiyu Wang, Baijiong Lin, Daochang Liu, Chang Xu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.11948)] \\\n23 Aug 2023\n\n**Boosting Diffusion Models with an Adaptive Momentum Sampler** \\\n*Xiyu Wang, Anh-Dung Dinh, Daochang Liu, Chang Xu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.11941)] \\\n23 Aug 2023\n\n**Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image** \\\n*Liao Shen, Xingyi Li, Huiqiang Sun, Juewen Peng, Ke Xian, Zhiguo Cao, Guosheng Lin* \\\nACM MM 2023. [[Paper](https://arxiv.org/abs/2308.10257)] \\\n20 Aug 2023\n\n**Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks** \\\n*Mingxuan Liu, Rui Wen, Hong Chen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.10187)] \\\n20 Aug 2023\n\n**SciRE-Solver: Efficient Sampling of Diffusion Probabilistic Models by Score-integrand Solver with Recursive Derivative Estimation** \\\n*Shigui Li, Wei Chen, Delu Zeng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.07896)] \\\n15 Aug 2023\n\n**Improved Order Analysis and Design of Exponential Integrator for Diffusion Models Sampling** \\\n*Qinsheng Zhang, Jiaming Song, Yongxin Chen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.02157)] \\\n4 Aug 2023\n\n**Patched Denoising Diffusion Models For High-Resolution Image Synthesis** \\\n*Zheng Ding, Mengqi Zhang, Jiajun Wu, Zhuowen Tu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2308.01316)] \\\n2 Aug 2023\n\n**Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models** \\\n*Xin Yuan, Linjie Li, Jianfeng Wang, Zhengyuan Yang, Kevin Lin, Zicheng Liu, Lijuan Wang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.14648)] \\\n27 Jul 2023\n\n**Synthesis of Batik Motifs using a Diffusion -- Generative Adversarial Network** \\\n*One Octadion, Novanto Yudistira, Diva Kurnianingtyas* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.12122)] \\\n22 Jul 2023\n\n**DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport** \\\n*Zezeng Li, ShengHao Li, Zhanpeng Wang, Na Lei, Zhongxuan Luo, Xianfeng Gu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.11308)] [[Github](https://github.com/cognaclee/DPM-OT)] \\\n21 Jul 2023\n\n**Diffusion Sampling with Momentum for Mitigating Divergence Artifacts** \\\n*Suttisak Wizadwongsa, Worameth Chinchuthakun, Pramook Khungurn, Amit Raj, Supasorn Suwajanakorn* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.11118)] \\\n20 Jul 2023\n\n**Flow Matching in Latent Space** \\\n*Quan Dao, Hao Phung, Binh Nguyen, Anh Tran* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.08698)] [[Project](https://vinairesearch.github.io/LFM/)] \\\n17 Jul 2023\n\n**Manifold-Guided Sampling in Diffusion Models for Unbiased Image Generation** \\\n*Xingzhe Su, Wenwen Qiang, Zeen Song, Hang Gao, Fengge Wu, Changwen Zheng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.08199)] \\\n17 Jul 2023\n\n**Complexity Matters: Rethinking the Latent Space for Generative Modeling** \\\n*Tianyang Hu, Fei Chen, Haonan Wang, Jiawei Li, Wenjia Wang, Jiacheng Sun, Zhenguo Li* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.08283)] \\\n17 Jul 2023\n\n**Collaborative Score Distillation for Consistent Visual Synthesis** \\\n*Subin Kim, Kyungmin Lee, June Suk Choi, Jongheon Jeong, Kihyuk Sohn, Jinwoo Shin* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.04787)] [[Project](https://subin-kim-cv.github.io/CSD/)] [[Github](https://github.com/subin-kim-cv/CSD)] \\\n4 Jul 2023\n\n**ProtoDiffusion: Classifier-Free Diffusion Guidance with Prototype Learning** \\\n*Gulcin Baykal, Halil Faruk Karagoz, Taha Binhuraib, Gozde Unal* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.01924)] \\\n4 Jul 2023\n\n**SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis** \\\n*Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, Robin Rombach* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.01952)] [[Github](https://github.com/Stability-AI/generative-models)] \\\n4 Jul 2023\n\n**Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation** \\\n*Tserendorj Adiya, Sanghun Kim, Jung Eun Lee, Jae Shin Yoon, Hwasup Lim* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2307.00574)] \\\n2 Jul 2023\n\n\n**Spiking Denoising Diffusion Probabilistic Models** \\\n*Jiahang Cao, Ziqing Wang, Hanzhong Guo, Hao Cheng, Qiang Zhang, Renjing Xu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.17046)] \\\n29 Jun 2023\n\n**DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data** \\\n*Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.14153)] \\\n25 Jun 2023\n\n**Decoupled Diffusion Models with Explicit Transition Probability** \\\n*Yuhang Huang, Zheng Qin, Xinwang Liu, Kai Xu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.13720)] \\\n23 Jun 2023\n\n**Continuous Layout Editing of Single Images with Diffusion Models** \\\n*Zhiyuan Zhang, Zhitong Huang, Jing Liao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.13078)] \\\n22 Jun 2023\n\n**Semi-Implicit Denoising Diffusion Models (SIDDMs)** \\\n*Yanwu Xu, Mingming Gong, Shaoan Xie, Wei Wei, Matthias Grundmann, kayhan Batmanghelich, Tingbo Hou* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.12511)] \\\n21 Jun 2023\n\n**Eliminating Lipschitz Singularities in Diffusion Models** \\\n*Zhantao Yang, Ruili Feng, Han Zhang, Yujun Shen, Kai Zhu, Lianghua Huang, Yifei Zhang, Yu Liu, Deli Zhao, Jingren Zhou, Fan Cheng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.11251)] \\\n20 Jun 2023\n\n**GD-VDM: Generated Depth for better Diffusion-based Video Generation** \\\n*Ariel Lapid, Idan Achituve, Lior Bracha, Ethan Fetaya* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.11173)] \\\n19 Jun 2023\n\n**Image Harmonization with Diffusion Model** \\\n*Jiajie Li, Jian Wang, Chen Wang, Jinjun Xiong* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.10441)] \\\n17 Jun 2023\n\n\n**Training Diffusion Classifiers with Denoising Assistance** \\\n*Chandramouli Sastry, Sri Harsha Dumpala, Sageev Oore* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.09192)] \\\n15 Jun 2023\n\n\n**Conditional Human Sketch Synthesis with Explicit Abstraction Control** \\\n*Dar-Yen Chen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.09274)] \\\n15 Jun 2023\n\n**Fast Training of Diffusion Models with Masked Transformers** \\\n*Hongkai Zheng, Weili Nie, Arash Vahdat, Anima Anandkumar* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.09305)] [[Github](https://github.com/Anima-Lab/MaskDiT)] \\\n15 Jun 2023\n\n\n**Relation-Aware Diffusion Model for Controllable Poster Layout Generation** \\\n*Fengheng Li, An Liu, Wei Feng, Honghe Zhu, Yaoyu Li, Zheng Zhang, Jingjing Lv, Xin Zhu, Junjie Shen, Zhangang Lin, Jingping Shao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.09086)] \\\n15 Jun 2023\n\n**OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models** \\\n*Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.08860)] \\\n15 Jun 2023\n\n\n**DORSal: Diffusion for Object-centric Representations of Scenes $\\textit{et al.}$** \\\n*Allan Jabri, Sjoerd van Steenkiste, Emiel Hoogeboom, Mehdi S. M. Sajjadi, Thomas Kipf* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.08068)] \\\n13 Jun 2023\n\n\n**Fast Diffusion Model** \\\n*Zike Wu, Pan Zhou, Kenji Kawaguchi, Hanwang Zhang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.06991)] [[Github](https://github.com/sail-sg/FDM)] \\\n12 Jun 2023\n\n**ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process** \\\n*Changyao Tian, Chenxin Tao, Jifeng Dai, Hao Li, Ziheng Li, Lewei Lu, Xiaogang Wang, Hongsheng Li, Gao Huang, Xizhou Zhu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.05423)] \\\n8 Jun 2023\n\n**Multi-Architecture Multi-Expert Diffusion Models** \\\n*Yunsung Lee, Jin-Young Kim, Hyojun Go, Myeongho Jeong, Shinhyeok Oh, Seungtaek Choi* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.04990)] \\\n8 Jun 2023\n\n**Interpreting and Improving Diffusion Models Using the Euclidean Distance Function** \\\n*Frank Permenter, Chenyang Yuan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.04848)] \\\n8 Jun 2023\n\n**Video Diffusion Models with Local-Global Context Guidance** \\\n*Siyuan Yang, Lu Zhang, Yu Liu, Zhizhuo Jiang, You He* \\\nIJCAI 2023. [[Paper](https://arxiv.org/abs/2306.02562)] [[Github](https://github.com/exisas/LGC-VD)] \\\n5 Jun 2023\n\n**Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models** \\\n*Andrew F. Luo, Margaret M. Henderson, Leila Wehbe, Michael J. Tarr* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.03089)] \\\n5 Jun 2023\n\n**Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching** \\\n*Etrit Haxholli, Marco Lorenzi* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.02658)] \\\n5 Jun 2023\n\n**Temporal Dynamic Quantization for Diffusion Models** \\\n*Junhyuk So, Jungwon Lee, Daehyun Ahn, Hyungjun Kim, Eunhyeok Park* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.02316)] \\\n4 Jun 2023\n\n**Conditional Generation from Unconditional Diffusion Models using Denoiser Representations** \\\n*Alexandros Graikos, Srikar Yellapragada, Dimitris Samaras* \\\nBMVC 2023. [[Paper](https://arxiv.org/abs/2306.01900)] [[Github](https://github.com/cvlab-stonybrook/fewshot-conditional-diffusion)] \\\n2 Jun 2023\n\n**Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation** \\\n*Nico Giambi, Giuseppe Lisanti* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.00914)] \\\n1 Jun 2023\n\n**Differential Diffusion: Giving Each Pixel Its Strength** \\\n*Eran Levin, Ohad Fried* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.00950)] \\\n1 Jun 2023\n\n\n**Addressing Discrepancies in Semantic and Visual Alignment in Neural Networks** \\\n*Natalie Abreu, Nathan Vaska, Victoria Helus* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.01148)] \\\n1 Jun 2023\n\n\n**Addressing Negative Transfer in Diffusion Models** \\\n*Hyojun Go, JinYoung Kim, Yunsung Lee, Seunghyun Lee, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2306.00354)] \\\n1 Jun 2023\n\n**A Geometric Perspective on Diffusion Models** \\\n*Defang Chen, Zhenyu Zhou, Jian-Ping Mei, Chunhua Shen, Chun Chen, Can Wang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.19947)] \\\n31 May 2023\n\n\n\n**Spontaneous symmetry breaking in generative diffusion models** \\\n*Gabriel Raya, Luca Ambrogioni* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.19693)] \\\n31 May 2023\n\n**Perturbation-Assisted Sample Synthesis: A Novel Approach for Uncertainty Quantification** \\\n*Yifei Liu, Rex Shen, Xiaotong Shen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.18671)] \\\n30 May 2023\n\n**One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models** \\\n*Ba-Hien Tran, Giulio Franzese, Pietro Michiardi, Maurizio Filippone* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.18900)] \\\n30 May 2023\n\n**Ambient Diffusion: Learning Clean Distributions from Corrupted Data** \\\n*Giannis Daras, Kulin Shah, Yuval Dagan, Aravind Gollakota, Alexandros G. Dimakis, Adam Klivans* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.19256)] \\\n30 May 2023\n\n**Towards Accurate Data-free Quantization for Diffusion Models** \\\n*Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie Zhou, Jiwen Lu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.18723)] \\\n30 May 2023\n\n**BRIGHT: Bi-level Feature Representation of Image Collections using Groups of Hash Tables** \\\n*Dingdong Yang, Yizhi Wang, Ali Mahdavi-Amiri, Hao Zhang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.18601)] [[Project](https://bright-project01.github.io/)] \\\n29 May 2023\n\n**Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models** \\\n*Weijian Luo, Tianyang Hu, Shifeng Zhang, Jiacheng Sun, Zhenguo Li, Zhihua Zhang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.18455)] \\\n29 May 2023\n\n**Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling** \\\n*Tianqi Chen, Mingyuan Zhou* \\\nICML 2023. [[Paper](https://arxiv.org/abs/2305.18375)] [[Github](https://github.com/tqch/poisson-jump)] \\\n28 May 2023\n\n**Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors** \\\n*Paul S. Scotti, Atmadeep Banerjee, Jimmie Goode, Stepan Shabalin, Alex Nguyen, Ethan Cohen, Aidan J. Dempster, Nathalie Verlinde, Elad Yundler, David Weisberg, Kenneth A. Norman, Tanishq Mathew Abraham* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.18274)] [[Github](https://medarc-ai.github.io/mindeye/)] \\\n29 May 2023\n\n**Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities** \\\n*Jingyuan Sun, Mingxiao Li, Zijiao Chen, Yunhao Zhang, Shaonan Wang, Marie-Francine Moens* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.17214)] \\\n26 May 2023\n\n**Parallel Sampling of Diffusion Models** \\\n*Andy Shih, Suneel Belkhale, Stefano Ermon, Dorsa Sadigh, Nima Anari* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.16317)] [[Github](https://github.com/AndyShih12/paradigms)] \\\n25 May 2023\n\n**Trans-Dimensional Generative Modeling via Jump Diffusion Models** \\\n*Andrew Campbell, William Harvey, Christian Weilbach, Valentin De Bortoli, Tom Rainforth, Arnaud Doucet* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.16261)] \\\n25 May 2023\n\n**UDPM: Upsampling Diffusion Probabilistic Models** \\\n*Shady Abu-Hussein, Raja Giryes* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.16269)] \\\n25 May 2023\n\n\n**Unifying GANs and Score-Based Diffusion as Generative Particle Models** \\\n*Jean-Yves Franceschi, Mike Gartrell, Ludovic Dos Santos, Thibaut Issenhuth, Emmanuel de Bézenac, Mickaël Chen, Alain Rakotomamonjy* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.16150)] \\\n25 May 2023\n\n**DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion** \\\n*Taesun Yeom, Minhyeok Lee* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.14849)] \\\n24 May 2023\n\n**Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps** \\\n*Mingxiao Li, Tingyu Qu, Wei Sun, Marie-Francine Moens* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.15583)] \\\n24 May 2023\n\n\n**Robust Classification via a Single Diffusion Model** \\\n*Huanran Chen, Yinpeng Dong, Zhengyi Wang, Xiao Yang, Chengqi Duan, Hang Su, Jun Zhu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.15241)] \\\n24 May 2023\n\n**On the Generalization of Diffusion Model** \\\n*Mingyang Yi, Jiacheng Sun, Zhenguo Li* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.14712)] \\\n24 May 2023\n\n**VDT: An Empirical Study on Video Diffusion with Transformers** \\\n*Haoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo, Zhiwu Lu, Ping Luo, Mingyu Ding* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.13311)] [[Github](https://github.com/RERV/VDT)] \\\n22 May 2023\n\n**Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity** \\\n*Zijiao Chen, Jiaxin Qing, Juan Helen Zhou* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.11675)] [[Project](https://mind-video.com/)] \\\n19 May 2023\n\n**PTQD: Accurate Post-Training Quantization for Diffusion Models** \\\n*Yefei He, Luping Liu, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.10657)] \\\n18 May 2023\n\n**Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces** \\\n*Javier E Santos, Zachary R. Fox, Nicholas Lubbers, Yen Ting Lin* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.11089)] \\\n18 May 2023\n\n**Structural Pruning for Diffusion Models** \\\n*Gongfan Fang, Xinyin Ma, Xinchao Wang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.10924)] [[Github](https://github.com/VainF/Diff-Pruning)] \\\n18 May 2023\n\n\n**Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling** \\\n*Shitong Shao, Xu Dai, Shouyi Yin, Lujun Li, Huanran Chen, Yang Hu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.10769)] \\\n18 May 2023\n\n**Controllable Mind Visual Diffusion Model** \\\n*Bohan Zeng, Shanglin Li, Xuhui Liu, Sicheng Gao, Xiaolong Jiang, Xu Tang, Yao Hu, Jianzhuang Liu, Baochang Zhang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.10135)] \\\n17 May 2023\n\n**Analyzing Bias in Diffusion-based Face Generation Models** \\\n*Malsha V. Perera, Vishal M. Patel* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.06402)] \\\n10 May 2023\n\n\n**Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs** \\\n*Kaiwen Zheng, Cheng Lu, Jianfei Chen, Jun Zhu* \\\nICML 2023. [[Paper](https://arxiv.org/abs/2305.03935)] \\\n6 May 2023\n\n**LEO: Generative Latent Image Animator for Human Video Synthesis** \\\n*Yaohui Wang, Xin Ma, Xinyuan Chen, Antitza Dantcheva, Bo Dai, Yu Qiao* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.03989)] [[Project](https://wyhsirius.github.io/LEO-project/)] [[Github](https://github.com/wyhsirius/LEO)] \\\n6 May 2023\n\n**Iterative α-(de)Blending: a Minimalist Deterministic Diffusion Model** \\\n*Eric Heitz, Laurent Belcour, Thomas Chambon* \\\nSIGGRAPH 2023. [[Paper](https://arxiv.org/abs/2305.03486)] \\\n5 May 2023\n\n\n**Reconstructing seen images from human brain activity via guided stochastic search** \\\n*Reese Kneeland, Jordyn Ojeda, Ghislain St-Yves, Thomas Naselaris* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2305.00556)] \\\n30 Apr 2023\n\n\n**Motion-Conditioned Diffusion Model for Controllable Video Synthesis** \\\n*Tsai-Shien Chen, Chieh Hubert Lin, Hung-Yu Tseng, Tsung-Yi Lin, Ming-Hsuan Yang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.14404)] [[Project](https://tsaishien-chen.github.io/MCDiff/)] \\\n27 Apr 2023\n\n**Score-based Generative Modeling Through Backward Stochastic Differential Equations: Inversion and Generation** \\\n*Zihao Wang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.13224)] \\\n26 Apr 2023\n\n**Exploring Compositional Visual Generation with Latent Classifier Guidance** \\\n*Changhao Shi, Haomiao Ni, Kai Li, Shaobo Han, Mingfu Liang, Martin Renqiang Min* \\\nCVPR Workshop 2023. [[Paper](https://arxiv.org/abs/2304.12536)] \\\n25 Apr 2023\n\n**Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models** \\\n*Zhendong Wang, Yifan Jiang, Huangjie Zheng, Peihao Wang, Pengcheng He, Zhangyang Wang, Weizhu Chen, Mingyuan Zhou* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.12526)] \\\n25 Apr 2023\n\n\n**Variational Diffusion Auto-encoder: Deep Latent Variable Model with Unconditional Diffusion Prior** \\\n*Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.12141)] \\\n24 Apr 2023\n\n\n**LaMD: Latent Motion Diffusion for Video Generation** \\\n*Yaosi Hu, Zhenzhong Chen, Chong Luo* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.11603)] \\\n23 Apr 2023\n\n\n**Lookahead Diffusion Probabilistic Models for Refining Mean Estimation** \\\n*Guoqiang Zhang, Niwa Kenta, W. Bastiaan Kleijn* \\\nCVPR 2023. [[Paper](https://arxiv.org/abs/2304.11312)] [[Github](https://github.com/guoqiang-zhang-x/LA-DPM)] \\\n22 Apr 2023\n\n**NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models** \\\n*Seung Wook Kim, Bradley Brown, Kangxue Yin, Karsten Kreis, Katja Schwarz, Daiqing Li, Robin Rombach, Antonio Torralba, Sanja Fidler* \\\nCVPR 2023. [[Paper](https://arxiv.org/abs/2304.09787)] \\\n19 Apr 2023\n\n**Attributing Image Generative Models using Latent Fingerprints** \\\n*Guangyu Nie, Changhoon Kim, Yezhou Yang, Yi Ren* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.09752)] \\\n17 Apr 2023\n\n\n**Identity Encoder for Personalized Diffusion** \\\n*Yu-Chuan Su, Kelvin C.K. Chan, Yandong Li, Yang Zhao, Han Zhang, Boqing Gong, Huisheng Wang, Xuhui Jia* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.07429)] \\\n14 Apr 2023\n\n**Memory Efficient Diffusion Probabilistic Models via Patch-based Generation** \\\n*Shinei Arakawa, Hideki Tsunashima, Daichi Horita, Keitaro Tanaka, Shigeo Morishima* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.07087)] \\\n14 Apr 2023\n\n**DCFace: Synthetic Face Generation with Dual Condition Diffusion Model** \\\n*Minchul Kim, Feng Liu, Anil Jain, Xiaoming Liu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.07060)] [[Github](https://github.com/mk-minchul/dcface)] \\\n14 Apr 2023\n\n**DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning** \\\n*Enze Xie, Lewei Yao, Han Shi, Zhili Liu, Daquan Zhou, Zhaoqiang Liu, Jiawei Li, Zhenguo Li* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.06648)] \\\n13 Apr 2023\n\n**RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment** \\\n*Hanze Dong, Wei Xiong, Deepanshu Goyal, Rui Pan, Shizhe Diao, Jipeng Zhang, Kashun Shum, Tong Zhang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.06767)] \\\n13 Apr 2023\n\n**DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion** \\\n*Johanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher-Shlizerman* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.06025)] [[Project](https://grail.cs.washington.edu/projects/dreampose/)] [[Github](https://github.com/johannakarras/DreamPose)] \\\n12 Apr 2023\n\n**Reflected Diffusion Models** \\\n*Aaron Lou, Stefano Ermon* \\\nICML 2023. [[Paper](https://arxiv.org/abs/2304.04740)] [[Project](https://aaronlou.com/blog/2023/reflected-diffusion/)] [[Github](https://github.com/louaaron/Reflected-Diffusion)] \\\n10 Apr 2023\n\n**Binary Latent Diffusion** \\\n*Ze Wang, Jiang Wang, Zicheng Liu, Qiang Qiu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.04820)] \\\n10 Apr 2023\n\n\n**Diffusion Models as Masked Autoencoders** \\\n*Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, Huiyu Wang, Cihang Xie, Alan Yuille, Christoph Feichtenhofer* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2304.03283)] [[Project](https://weichen582.github.io/diffmae.html)] \\\n6 Apr 2023\n\n**Few-shot Semantic Image Synthesis with Class Affinity Transfer** \\\n*Marlène Careil, Jakob Verbeek, Stéphane Lathuilière* \\\nCVPR 2023. [[Paper](https://arxiv.org/abs/2304.02321)] \\\n5 Apr 2023\n\n\n**EGC: Image Generation and Classification via a Diffusion Energy-Based Model** \\\n*Qiushan Guo, Chuofan Ma, Yi Jiang, Zehuan Yuan, Yizhou Yu, Ping Luo* \\\narxiv 2023. [[Paper](https://arxiv.org/abs/2304.02012)] [[Project](https://guoqiushan.github.io/egc.github.io/)] \\\n4 Apr 2023\n\n\n\n**Token Merging for Fast Stable Diffusion** \\\n*Daniel Bolya, Judy Hoffman* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.17604)] [[Github](https://github.com/dbolya/tomesd)] \\\n30 Mar 2023\n\n**A Closer Look at Parameter-Efficient Tuning in Diffusion Models** \\\n*Chendong Xiang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.18181)] \\\n31 Mar 2023\n\n**-Diff: Infinite Resolution Diffusion with Subsampled Mollified States** \\\n*Sam Bond-Taylor, Chris G. Willcocks* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.18242)] \\\n31 Mar 2023\n\n**3D-aware Image Generation using 2D Diffusion Models** \\\n*Jianfeng Xiang, Jiaolong Yang, Binbin Huang, Xin Tong* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.17905)] [[Project](https://jeffreyxiang.github.io/ivid/)] \\\n31 Mar 2023\n\n**Consistent View Synthesis with Pose-Guided Diffusion Models** \\\n*Hung-Yu Tseng, Qinbo Li, Changil Kim, Suhib Alsisan, Jia-Bin Huang, Johannes Kopf* \\\nCVPR 2023. [[Paper](https://arxiv.org/abs/2303.17598)] \\\n30 Mar 2023\n\n\n**DiffCollage: Parallel Generation of Large Content with Diffusion Models** \\\n*Qinsheng Zhang, Jiaming Song, Xun Huang, Yongxin Chen, Ming-Yu Liu* \\\nCVPR 2023. [[Paper](https://arxiv.org/abs/2303.17076)] [[Project](https://research.nvidia.com/labs/dir/diffcollage/)] \\\n30 Mar 2023\n\n**Masked Diffusion Transformer is a Strong Image Synthesizer** \\\n*Shanghua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan* \\\narXiv 2023.  [[Paper](https://arxiv.org/abs/2303.14389)] [[Github](https://github.com/sail-sg/MDT)] \\\n25 Mar 2023\n\n**Conditional Image-to-Video Generation with Latent Flow Diffusion Models** \\\n*Haomiao Ni, Changhao Shi, Kai Li, Sharon X. Huang, Martin Renqiang Min* \\\nCVPR 2023. [[Paper](https://arxiv.org/abs/2303.13744)] [[Github](https://github.com/nihaomiao/CVPR23_LFDM)] \\\n24 Mar 2023\n\n**NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation** \\\n*Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, Jianlong Fu, Gong Ming, Lijuan Wang, Zicheng Liu, Houqiang Li, Nan Duan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.12346)] [[Project](https://msra-nuwa.azurewebsites.net/#/)] \\\n22 Mar 2023\n\n**Object-Centric Slot Diffusion** \\\n*Jindong Jiang, Fei Deng, Gautam Singh, Sungjin Ahn* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.10834)] \\\n20 Mar 2023\n\n\n**LDMVFI: Video Frame Interpolation with Latent Diffusion Models** \\\n*Duolikun Danier, Fan Zhang, David Bull* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.09508)] \\\n16 Mar 2023\n\n**Efficient Diffusion Training via Min-SNR Weighting Strategy** \\\n*Tiankai Hang, Shuyang Gu, Chen Li, Jianmin Bao, Dong Chen, Han Hu, Xin Geng, Baining Guo* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.09556)] \\\n16 Mar 2023\n\n**VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation** \\\nCVPR 2023. [[Paper](https://arxiv.org/abs/2303.08320)] \\\n15 Mar 2023\n\n**Interpretable ODE-style Generative Diffusion Model via Force Field Construction** \\\n*Weiyang Jin, Yongpei Zhu, Yuxi Peng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.08063)] \\\n14 Mar 2023\n\n**Regularized Vector Quantization for Tokenized Image Synthesis** \\\n*Jiahui Zhang, Fangneng Zhan, Christian Theobalt, Shijian Lu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.06424)] \\\n11 Mar 2023\n\n\n**PARASOL: Parametric Style Control for Diffusion Image Synthesis** \\\n*Gemma Canet Tarrés, Dan Ruta, Tu Bui, John Collomosse* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.06464)] \\\n11 Mar 2023\n\n**Brain-Diffuser: Natural scene reconstruction from fMRI signals using generative latent diffusion** \\\n*Furkan Ozcelik, Rufin VanRullen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.05334)] \\\n9 Mar 2023\n\n**Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation** \\\n*Paul Hagemann, Lars Ruthotto, Gabriele Steidl, Nicole Tianjiao Yang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.04772)] \\\n8 Mar 2023\n\n\n**TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation** \\\n*David Berthelot, Arnaud Autef, Jierui Lin, Dian Ang Yap, Shuangfei Zhai, Siyuan Hu, Daniel Zheng, Walter Talbott, Eric Gu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.04248)] \\\n7 Mar 2023\n\n**Generative Diffusions in Augmented Spaces: A Complete Recipe** \\\n*Kushagra Pandey, Stephan Mandt* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.01748)] \\\n3 Mar 2023\n\n**Consistency Models** \\\n*Yang Song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.01469)] \\\n2 Mar 2023\n\n**Diffusion Probabilistic Fields** \\\n*Peiye Zhuang, Samira Abnar, Jiatao Gu, Alex Schwing, Joshua M. Susskind, Miguel Ángel Bautista* \\\nICLR 2023. [[Paper](https://arxiv.org/abs/2303.00165)] \\\n1 Mar 2023\n\n**Unsupervised Discovery of Semantic Latent Directions in Diffusion Models** \\\n*Yong-Hyun Park, Mingi Kwon, Junghyo Jo, Youngjung Uh* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.12469)] \\\n24 Feb 2023\n\n**Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC** \\\n*Yilun Du, Conor Durkan, Robin Strudel, Joshua B. Tenenbaum, Sander Dieleman, Rob Fergus, Jascha Sohl-Dickstein, Arnaud Doucet, Will Grathwohl* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.11552)] [[Project](https://energy-based-model.github.io/reduce-reuse-recycle/)] \\\n22 Feb 2023\n\n**Learning 3D Photography Videos via Self-supervised Diffusion on Single Images** \\\n*Xiaodong Wang, Chenfei Wu, Shengming Yin, Minheng Ni, Jianfeng Wang, Linjie Li, Zhengyuan Yang, Fan Yang, Lijuan Wang, Zicheng Liu, Yuejian Fang, Nan Duan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.10781)] \\\n21 Feb 2023\n\n**On Calibrating Diffusion Probabilistic Models** \\\n*Tianyu Pang, Cheng Lu, Chao Du, Min Lin, Shuicheng Yan, Zhijie Deng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.10688)] [[Github](https://github.com/thudzj/Calibrated-DPMs)] \\\n21 Feb 2023\n\n**Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels** \\\n*Zebin You, Yong Zhong, Fan Bao, Jiacheng Sun, Chongxuan Li, Jun Zhu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.10586)] \\\n21 Feb 2023\n\n**Cross-domain Compositing with Pretrained Diffusion Models** \\\n*Roy Hachnochi, Mingrui Zhao, Nadav Orzech, Rinon Gal, Ali Mahdavi-Amiri, Daniel Cohen-Or, Amit Haim Bermano* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.10167)] [[Github](https://github.com/cross-domain-compositing/cross-domain-compositing)] \\\n20 Feb 2023\n\n\n\n**Restoration based Generative Models** \\\n*Jaemoo Choi, Yesom Park, Myungjoo Kang* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2303.05456)] \\\n20 Feb 2023\n\n\n\n**Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent** \\\n*Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.09057)] [[Github](https://github.com/giannisdaras/cdm)] \\\n17 Feb 2023\n\n**LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation** \\\n*Jiaxin Cheng, Xiao Liang, Xingjian Shi, Tong He, Tianjun Xiao, Mu Li* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.08908)] \\\n16 Feb 2023\n\n**Video Probabilistic Diffusion Models in Projected Latent Space** \\\n*Sihyun Yu, Kihyuk Sohn, Subin Kim, Jinwoo Shin* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.07685)] [[Github](https://sihyun.me/PVDM/)] \\\n15 Feb 2023\n\n**DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model** \\\n*Yichen Peng, Chunqi Zhao, Haoran Xie, Tsukasa Fukusato, Kazunori Miyata* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.06908)] \\\n14 Feb 2023\n\n**Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions** \\\n*Raghav Singhal, Mark Goldstein, Rajesh Ranganath* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.07261)] \\\n14 Feb 2023\n\n\n**Preconditioned Score-based Generative Models** \\\n*Li Zhang, Hengyuan Ma, Xiatian Zhu, Jianfeng Feng* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.06504)] [Github](https://github.com/fudan-zvg/PDS)] \\\n13 Feb 2023\n\n**Star-Shaped Denoising Diffusion Probabilistic Models** \\\n*Andrey Okhotin, Dmitry Molchanov, Vladimir Arkhipkin, Grigory Bartosh, Aibek Alanov, Dmitry Vetrov* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.05259)] \\\n10 Feb 2023 \n\n\n**UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models** \\\n*Wenliang Zhao, Lujia Bai, Yongming Rao, Jie Zhou, Jiwen Lu* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.04867)] [[Project](https://unipc.ivg-research.xyz)] [[Github](https://github.com/wl-zhao/UniPC)] \\\n9 Feb 2023\n\n**Geometry of Score Based Generative Models** \\\n*Sandesh Ghimire, Jinyang Liu, Armand Comas, Davin Hill, Aria Masoomi, Octavia Camps, Jennifer Dy* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.04411)] \\\n9 Feb 2023\n\n**Q-Diffusion: Quantizing Diffusion Models** \\\n*Xiuyu Li, Long Lian, Yijiang Liu, Huanrui Yang, Zhen Dong, Daniel Kang, Shanghang Zhang, Kurt Keutzer* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.04304)] \\\n8 Feb 2023\n\n**PFGM++: Unlocking the Potential of Physics-Inspired Generative Models** \\\n*Yilun Xu, Ziming Liu, Yonglong Tian, Shangyuan Tong, Max Tegmark, Tommi Jaakkola* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.04265)] [[Github](https://github.com/Newbeeer/pfgmpp)] \\\n8 Feb 2023\n\n**Long Horizon Temperature Scaling** \\\n*Andy Shih, Dorsa Sadigh, Stefano Ermon* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.03686)] \\\n7 Feb 2023\n\n**Spatial Functa: Scaling Functa to ImageNet Classification and Generation** \\\n*Matthias Bauer, Emilien Dupont, Andy Brock, Dan Rosenbaum, Jonathan Schwarz, Hyunjik Kim* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.03130)] \\\n6 Feb 2023\n\n**ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories** \\\n*Zijian Zhang, Zhou Zhao, Jun Yu, Qi Tian* \\\nAAAI 2023. [[Paper](https://arxiv.org/abs/2302.02373)] \\\n5 Feb 2023\n\n**Divide and Compose with Score Based Generative Models** \\\n*Sandesh Ghimire, Armand Comas, Davin Hill, Aria Masoomi, Octavia Camps, Jennifer Dy* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2302.02272)] [[Github](https://github.com/sandeshgh/Score-based-disentanglement)] \\\n5 Feb 2023\n\n\n**Stable Target Field for Reduced Variance Score Estimation in Diffusion Models** \\\n*Yilun Xu, Shangyuan Tong, Tommi Jaakkola* \\\nICLR 2023. [[Paper](https://arxiv.org/abs/2302.00670)] [[Github](https://github.com/Newbeeer/stf)] \\\n1 Feb 2023\n\n**DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models** \\\n*Tao Yang, Yuwang Wang, Yan Lv, Nanning Zheng* \\\nNeurIPS 2023. [[Paper](https://arxiv.org/abs/2301.13721)] \\\n31 Jan 2023\n\n\n**Optimizing DDPM Sampling with Shortcut Fine-Tuning** \\\n*Ying Fan, Kangwook Lee* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.13362)] \\\n31 Jan 2023\n\n**Learning Data Representations with Joint Diffusion Models** \\\n*Kamil Deja, Tomasz Trzcinski, Jakub M. Tomczak* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.13622)] \\\n31 Jan 2023\n\n**ERA-Solver: Error-Robust Adams Solver for Fast Sampling of Diffusion Probabilistic Models** \\\n*Shengmeng Li, Luping Liu, Zenghao Chai, Runnan Li, Xu Tan* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.12935)] \\\n30 Jan 2023\n\n**Don't Play Favorites: Minority Guidance for Diffusion Models** \\\n*Soobin Um, Jong Chul Ye* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.12334)] [[Github](https://github.com/sangyun884/fast-ode)] \\\n29 Jan 2023\n\n**Accelerating Guided Diffusion Sampling with Splitting Numerical Methods** \\\n*Suttisak Wizadwongsa, Supasorn Suwajanakorn* \\\nICLR 2023. [[Paper](https://arxiv.org/abs/2301.11558)] \\\n27 Jan 2023\n\n**Input Perturbation Reduces Exposure Bias in Diffusion Models** \\\n*Mang Ning, Enver Sangineto, Angelo Porrello, Simone Calderara, Rita Cucchiara* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.11706)] [[Github](https://github.com/forever208/DDPM-IP)] \\\n27 Jan 2023\n\n**Minimizing Trajectory Curvature of ODE-based Generative Models** \\\n*Sangyun Lee, Beomsu Kim, Jong Chul Ye* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.12003)] \\\n27 Jan 2023\n\n\n**On the Importance of Noise Scheduling for Diffusion Models** \\\n*Ting Chen* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.10972)] \\\n26 Jan 2023\n\n**simple diffusion: End-to-end diffusion for high resolution images** \\\n*Emiel Hoogeboom, Jonathan Heek, Tim Salimans* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.11093)] \\\n26 Jan 2023\n\n**Fast Inference in Denoising Diffusion Models via MMD Finetuning** \\\n*Emanuele Aiello, Diego Valsesia, Enrico Magli* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2301.07969)] [[Github](https://github.com/diegovalsesia/MMD-DDM)] \\\n19 Jan 2023\n\n**Exploring Transformer Backbones for Image Diffusion Models** \\\n*Princy Chahal* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.14678)] \\\n27 Dec 2022\n\n**Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models** \\\n*Zijian Zhang, Zhou Zhao, Zhijie Lin* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.12990)] \\\n26 Dec 2022\n\n\n**Scalable Adaptive Computation for Iterative Generation** \\\n*Allan Jabri, David Fleet, Ting Chen* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.11972)] \\\n22 Dec 2022\n\n**Hierarchically branched diffusion models for efficient and interpretable multi-class conditional generation** \\\n*Alex M. Tseng, Tommaso Biancalani, Max Shen, Gabriele Scalia* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.10777)] \\\n21 Dec 2022\n\n\n**MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation** \\\n*Ludan Ruan, Yiyang Ma, Huan Yang, Huiguo He, Bei Liu, Jianlong Fu, Nicholas Jing Yuan, Qin Jin, Baining Guo* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.09478)] [[Github](https://github.com/researchmm/MM-Diffusion)] \\\n19 Dec 2022\n\n\n**Scalable Diffusion Models with Transformers** \\\n*William Peebles, Saining Xie* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.09748)] [[Project](https://www.wpeebles.com/DiT)] [[Github](https://github.com/facebookresearch/DiT)] \\\n19 Dec 2022\n\n\n**DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models** \\\n*Gyeongnyeon Kim, Wooseok Jang, Gyuseong Lee, Susung Hong, Junyoung Seo, Seungryong Kim* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.08861)] [[Project](https://ku-cvlab.github.io/DAG/)] \\\n17 Dec 2022\n\n\n**Towards Practical Plug-and-Play Diffusion Models** \\\n*Hyojun Go, Yunsung Lee, Jin-Young Kim, Seunghyun Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.05973)] \\\n12 Dec 2022\n\n**Semantic Brain Decoding: from fMRI to conceptually similar image reconstruction of visual stimuli** \\\n*Matteo Ferrante, Tommaso Boccato, Nicola Toschi* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.06726)] \\\n13 Dec 2022\n\n**MAGVIT: Masked Generative Video Transformer** \\\n*Lijun Yu, Yong Cheng, Kihyuk Sohn, José Lezama, Han Zhang, Huiwen Chang, Alexander G. Hauptmann, Ming-Hsuan Yang, Yuan Hao, Irfan Essa, Lu Jiang* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.05199)] [Project](https://magvit.cs.cmu.edu/)] \\\n10 Dec 2022\n\n**Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding** \\\n*Gyeongman Kim, Hajin Shim, Hyunsu Kim, Yunjey Choi, Junho Kim, Eunho Yang* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.02802)] \\\n6 Dec 2022\n\n**Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models** \\\n*Naoki Matsunaga, Masato Ishii, Akio Hayakawa, Kenji Suzuki, Takuya Narihira* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.02024)] \\\n5 Dec 2022\n\n\n**VIDM: Video Implicit Diffusion Models** \\\n*Kangfu Mei, Vishal M. Patel* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.00235)] [[Project](https://kfmei.page/vidm/)] [[Github](https://github.com/MKFMIKU/VIDM)] \\\n1 Dec 2022\n\n**Why Are Conditional Generative Models Better Than Unconditional Ones?** \\\n*Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2212.00362)] \\\n1 Dec 2022\n\n\n**High-Fidelity Guided Image Synthesis with Latent Diffusion Models** \\\n*Jaskirat Singh, Stephen Gould, Liang Zheng* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.17084)] [[Project](https://1jsingh.github.io/gradop)] \\\n30 Nov 2022\n\n\n**Score-based Continuous-time Discrete Diffusion Models** \\\n*Haoran Sun, Lijun Yu, Bo Dai, Dale Schuurmans, Hanjun Dai* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.16750)] \\\n30 Nov 2022\n\n**Wavelet Diffusion Models are fast and scalable Image Generators** \\\n*Hao Phung, Quan Dao, Anh Tran* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.16152)] \\\n29 Nov 2022\n\n\n**Dimensionality-Varying Diffusion Process** \\\n*Han Zhang, Ruili Feng, Zhantao Yang, Lianghua Huang, Yu Liu, Yifei Zhang, Yujun Shen, Deli Zhao, Jingren Zhou, Fan Cheng* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.16032)] \\\n29 Nov 2022\n\n**Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models** \\\n*Dongjun Kim, Yeongmin Kim, Wanmo Kang, Il-Chul Moon* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.17091)] \\\n28 Nov 2022\n\n\n\n**Diffusion Probabilistic Model Made Slim** \\\n*Xingyi Yang, Daquan Zhou, Jiashi Feng, Xinchao Wang* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.17106)] \\\n27 Nov 2022\n\n\n**Fast Sampling of Diffusion Models via Operator Learning** \\\n*Hongkai Zheng, Weili Nie, Arash Vahdat, Kamyar Azizzadenesheli, Anima Anandkumar* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.13449)] \\\n24 Nov 2022\n\n**Latent Video Diffusion Models for High-Fidelity Video Generation with Arbitrary Lengths** \\\n*Yingqing He, Tianyu Yang, Yong Zhang, Ying Shan, Qifeng Chen* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.13221)] \\\n23 Nov 2022\n\n\n\n**Paint by Example: Exemplar-based Image Editing with Diffusion Models** \\\n*Binxin Yang, Shuyang Gu, Bo Zhang, Ting Zhang, Xuejin Chen, Xiaoyan Sun, Dong Chen, Fang Wen* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.13227)] \\\n23 Nov 2022\n\n\n**SinDiffusion: Learning a Diffusion Model from a Single Natural Image** \\\n*Weilun Wang, Jianmin Bao, Wengang Zhou, Dongdong Chen, Dong Chen, Lu Yuan, Houqiang Li* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.12445)] [[Github](https://github.com/WeilunWang/SinDiffusion)] \\\n22 Nov 2022\n\n**Accelerating Diffusion Sampling with Classifier-based Feature Distillation** \\\n*Wujie Sun, Defang Chen, Can Wang, Deshi Ye, Yan Feng, Chun Chen* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.12039)] \\\n22 Nov 2022\n\n**SceneComposer: Any-Level Semantic Image Synthesis** \\\n*Yu Zeng, Zhe Lin, Jianming Zhang, Qing Liu, John Collomosse, Jason Kuen, Vishal M. Patel* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.11742)] [[Project](https://zengyu.me/scenec/)] \\\n21 Nov 2022\n\n**Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training** \\\n*Ling Yang, Zhilin Huang, Yang Song, Shenda Hong, Guohao Li, Wentao Zhang, Bin Cui, Bernard Ghanem, Ming-Hsuan Yang* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.11138)] \\\n21 Nov 2022\n\n**SinFusion: Training Diffusion Models on a Single Image or Video** \\\n*Yaniv Nikankin, Niv Haim, Michal Irani* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.11743)] \\\n21 Nov 2022\n\n**MagicVideo: Efficient Video Generation With Latent Diffusion Models** \\\n*Daquan Zhou, Weimin Wang, Hanshu Yan, Weiwei Lv, Yizhe Zhu, Jiashi Feng* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.11018)] [[Project](https://magicvideo.github.io/)] \\\n20 Nov 2022\n\n**Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding** \\\n*Zijiao Chen, Jiaxin Qing, Tiange Xiang, Wan Lin Yue, Juan Helen Zhou* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.06956)] [[Project](https://mind-vis.github.io/)] [[Github](https://github.com/zjc062/mind-vis)] \\\n13 Nov 2022\n\n**Few-shot Image Generation with Diffusion Models** \\\n*Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.03264)] \\\n7 Nov 2022\n\n**From Denoising Diffusions to Denoising Markov Models** \\\n*Joe Benton, Yuyang Shi, Valentin De Bortoli, George Deligiannidis, Arnaud Doucet* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.03595)] [[Github](https://github.com/yuyang-shi/generalized-diffusion)] \\\n7 Nov 2022\n\n\n**Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models** \\\n*Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, Song Han, Jun-Yan Zhu* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2211.02048)] [[Github](https://github.com/lmxyy/sige)] \\\n4 Nov 2022\n\n**An optimal control perspective on diffusion-based generative modeling** \\\n*Julius Berner, Lorenz Richter, Karen Ullrich* \\\nNeurIPS Workshop 2022. [[Paper](https://arxiv.org/abs/2211.01364)] \\\n2 Nov 2022\n\n**Entropic Neural Optimal Transport via Diffusion Processes** \\\n*Nikita Gushchin, Alexander Kolesov, Alexander Korotin, Dmitry Vetrov, Evgeny Burnaev* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2211.01156)] \\\n2 Nov 2022\n\n**DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models** \\\n*Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu* \\\nNeurIPS 2022 (Oral). [[Paper](https://arxiv.org/abs/2211.01095)] [[Github](https://github.com/LuChengTHU/dpm-solver)] \\\n2 Nov 2022\n\n**Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models** \\\n*Vikram Voleti, Christopher Pal, Adam Oberman* \\\nNeurIPS Workshop 2022. [[Paper](https://arxiv.org/abs/2210.12254)] \\\n21 Oct 2022\n\n\n**Deep Equilibrium Approaches to Diffusion Models** \\\n*Ashwini Pokle, Zhengyang Geng, Zico Kolter* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2210.12867)] [[Github](https://github.com/locuslab/deq-ddim)] \\\n23 Oct 2022\n\n**Representation Learning with Diffusion Models** \\\n*Jeremias Traub* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.11058)] [[Github](https://github.com/jeremiastraub/diffusion)] \\\n20 Oct 2022\n\n**Self-Guided Diffusion Models** \\\n*Vincent Tao Hu, David W Zhang, Yuki M. Asano, Gertjan J. Burghouts, Cees G. M. Snoek* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.06462)] [[Project](http://taohu.me/sgdm/)] \\\n12 Oct 2022\n\n**GENIE: Higher-Order Denoising Diffusion Solvers** \\\n*Tim Dockhorn, Arash Vahdat, Karsten Kreis* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2210.05475)] [[Project](https://nv-tlabs.github.io/GENIE/) [[Github](https://github.com/nv-tlabs/GENIE)] \\\n11 Oct 2022\n\n**f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation** \\\n*Jiatao Gu, Shuangfei Zhai, Yizhe Zhang, Miguel Angel Bautista, Josh Susskind* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.04955)] [[Project](http://jiataogu.me/fdm/)] \\\n10 Oct 2022\n\n**On Distillation of Guided Diffusion Models** \\\n*Chenlin Meng, Ruiqi Gao, Diederik P. Kingma, Stefano Ermon, Jonathan Ho, Tim Salimans* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.03142)] \\\n6 Oct 2022\n\n\n**Improving Sample Quality of Diffusion Model Using Self-Attention Guidance** \\\n*Susung Hong, Gyuseong Lee, Wooseok Jang, Seungryong Kim* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.00939)] [[Project](https://ku-cvlab.github.io/Self-Attention-Guidance/)] \\\n3 Oct 2022\n\n**OCD: Learning to Overfit with Conditional Diffusion Models** \\\n*Shahar Shlomo Lutati, Lior Wolf* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.00471)] [[Github](https://github.com/ShaharLutatiPersonal/OCD)] \\\n2 Oct 2022\n\n**Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2** \\\n*Ali Borji* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2210.00586)] [[Github](https://github.com/aliborji/GFW)] \\\n2 Oct 2022\n\n**Denoising MCMC for Accelerating Diffusion-Based Generative Models** \\\n*Beomsu Kim, Jong Chul Ye* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.14593)] [[Github](https://github.com/1202kbs/DMCMC)] \\\n29 Sep 2022\n\n**All are Worth Words: a ViT Backbone for Score-based Diffusion Models** \\\n*Fan Bao, Chongxuan Li, Yue Cao, Jun Zhu* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.12152)] \\\n25 Sep 2022\n\n\n**Neural Wavelet-domain Diffusion for 3D Shape Generation** \\\n*Ka-Hei Hui, Ruihui Li, Jingyu Hu, Chi-Wing Fu* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.08725)] \\\n19 Sep 2022\n\n**Can segmentation models be trained with fully synthetically generated data?** \\\n*Virginia Fernandez, Walter Hugo Lopez Pinaya, Pedro Borges, Petru-Daniel Tudosiu, Mark S Graham, Tom Vercauteren, M Jorge Cardoso* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.08256)] \\\n17 Sep 2022\n\n**Blurring Diffusion Models** \\\n*Emiel Hoogeboom, Tim Salimans* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.05557)] \\\n12 Sep 2022\n\n**Soft Diffusion: Score Matching for General Corruptions** \\\n*Giannis Daras, Mauricio Delbracio, Hossein Talebi, Alexandros G. Dimakis, Peyman Milanfar* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.05442)] \\\n12 Sep 2022\n\n**Improved Masked Image Generation with Token-Critic** \\\n*José Lezama, Huiwen Chang, Lu Jiang, Irfan Essa* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2209.04439)] \\\n9 Sep 2022\n\n\n**Let us Build Bridges: Understanding and Extending Diffusion Generative Models** \\\n*Xingchao Liu, Lemeng Wu, Mao Ye, Qiang Liu* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.14699)] \\\n31 Aug 2022\n\n**Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis** \\\n*Wan-Cyuan Fan, Yen-Chun Chen, DongDong Chen, Yu Cheng, Lu Yuan, Yu-Chiang Frank Wang* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.13753)] \\\n29 Aug 2022\n\n\n**Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model** \\\n*Shin-I Cheng, Yu-Jie Chen, Wei-Chen Chiu, Hsin-Ying Lee, Hung-Yu Tseng* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.12675)] [[Project](https://cyj407.github.io/DiSS/)] \\\n26 Aug 2022\n\n**Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise** \\\n*Arpit Bansal, Eitan Borgnia, Hong-Min Chu, Jie S. Li, Hamid Kazemi, Furong Huang, Micah Goldblum, Jonas Geiping, Tom Goldstein* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.09392)] [[Github](https://github.com/arpitbansal297/Cold-Diffusion-Models)] \\\n19 Aug 2022\n\n**Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance** \\\n*Bahjat Kawar, Roy Ganz, Michael Elad* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.08664)] \\\n18 Aug 2022\n\n**Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model** \\\n*Xiulong Yang, Sheng-Min Shih, Yinlin Fu, Xiaoting Zhao, Shihao Ji* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.07791)] [[Github](https://github.com/sndnyang/Diffusion_ViT)] \\\n16 Aug 2022\n\n\n\n**Applying Regularized Schrödinger-Bridge-Based Stochastic Process in Generative Modeling** \\\n*Ki-Ung Song* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.07131)] [[Github](https://github.com/KiUngSong/RSB)] \\\n15 Aug 2022\n\n**Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning** \\\n*Ting Chen, Ruixiang Zhang, Geoffrey Hinton* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.04202)] \\\n8 Aug 2022\n\n\n**Pyramidal Denoising Diffusion Probabilistic Models** \\\n*Dohoon Ryu, Jong Chul Ye* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2208.01864)] \\\n3 Aug 2022\n\n**Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis** \\\n*Sangyun Lee, Hyungjin Chung, Jaehyeon Kim, Jong Chul Ye* \\\narxiv 2022. [[Paper](https://arxiv.org/abs/2207.11192)] [[Github](https://github.com/sangyun884/blur-diffusion)] \\\n16 Jul 2022\n\n**Improving Diffusion Model Efficiency Through Patching** \\\n*Troy Luhman, Eric Luhman* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2207.04316)] [[Github](https://github.com/ericl122333/PatchDiffusion-Pytorch)] \\\n9 Jul 2022\n\n**Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling** \\\n*Hengyuan Ma, Li Zhang, Xiatian Zhu, Jianfeng Feng* \\\nECCV 2022. [[Paper](https://arxiv.org/abs/2207.02196)] \\\n5 Jul 2022\n\n**SPI-GAN: Distilling Score-based Generative Models with Straight-Path Interpolations** \\\n*Jinsung Jeon, Noseong Park* \\\narxiv 2022. [[Paper](https://arxiv.org/abs/2206.14464)] \\\n29 Jun 2022\n\n**Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation** \\\n*Shengming Li, Guangcong Zheng, Hui Wang, Taiping Yao, Yang Chen, Shoudong Ding, Xi Li* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.11474)] \\\n23 Jun 2022\n\n**Generative Modelling With Inverse Heat Dissipation** \\\n*Severi Rissanen, Markus Heinonen, Arno Solin* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.13397)] [[Project](https://aaltoml.github.io/generative-inverse-heat-dissipation/)] \\\n21 Jun 2022\n\n**Diffusion models as plug-and-play priors** \\\n*Alexandros Graikos, Nikolay Malkin, Nebojsa Jojic, Dimitris Samaras* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2206.09012)] [[Github](https://github.com/alexgraikos/diffusion_priors)] \\\n17 Jun 2022\n\n**A Flexible Diffusion Model** \\\n*Weitao Du, Tao Yang, He Zhang, Yuanqi Du* \\\nICML 2023. [[Paper](https://arxiv.org/abs/2206.10365)] \\\n17 Jun 2022\n\n**Lossy Compression with Gaussian Diffusion** \\\n*Lucas Theis, Tim Salimans, Matthew D. Hoffman, Fabian Mentzer* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.08889)] \\\n17 Jun 2022\n\n**Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching** \\\n*Cheng Lu, Kaiwen Zheng, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu* \\\nICML 2022. [[Paper](https://arxiv.org/abs/2206.08265)] [[Github](https://github.com/LuChengTHU/mle_score_ode)] \\\n16 Jun 2022\n\n**Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models** \\\n*Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu, Bo Zhang* \\\nICML 2022. [[Paper](https://arxiv.org/abs/2206.07309)] [[Github](https://github.com/baofff/Extended-Analytic-DPM)] \\\n15 Jun 2022\n\n\n**Diffusion Models for Video Prediction and Infilling** \\\n*Tobias Höppe, Arash Mehrjou, Stefan Bauer, Didrik Nielsen, Andrea Dittadi* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.07696)] \\\n15 Jun 2022\n\n**Discrete Contrastive Diffusion for Cross-Modal and Conditional Generation** \\\n*Ye Zhu, Yu Wu, Kyle Olszewski, Jian Ren, Sergey Tulyakov, Yan Yan* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.07771)] [[Github](https://github.com/L-YeZhu/CDCD)] \\\n15 Jun 2022\n\n**gDDIM: Generalized denoising diffusion implicit models** \\\n*Qinsheng Zhang, Molei Tao, Yongxin Chen* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.05564)] [[Github](https://github.com/qsh-zh/gDDIM)] \\\n11 Jun 2022\n\n**How Much is Enough? A Study on Diffusion Times in Score-based Generative Models** \\\n*Giulio Franzese, Simone Rossi, Lixuan Yang, Alessandro Finamore, Dario Rossi, Maurizio Filippone, Pietro Michiardi* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.05173)] \\\n10 Jun 2022\n\n**Image Generation with Multimodal Priors using Denoising Diffusion Probabilistic Models** \\\n*Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, Vishal M Patel* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.05039)] \\\n10 Jun 2022\n\n**Accelerating Score-based Generative Models for High-Resolution Image Synthesis** \\\n*Hengyuan Ma, Li Zhang, Xiatian Zhu, Jingfeng Zhang, Jianfeng Feng* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.04029)] \\\n8 Jun 2022\n\n**Diffusion-GAN: Training GANs with Diffusion** \\\n*Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2206.02262)] \\\n5 Jun 2022\n\n**DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps** \\\n*Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu* \\\nNeurrIPS 2022. [[Paper](https://arxiv.org/abs/2206.00927)] [[Github](https://github.com/LuChengTHU/dpm-solver)] \\\n2 Jun 2022\n\n**Elucidating the Design Space of Diffusion-Based Generative Models** \\\n*Tero Karras, Miika Aittala, Timo Aila, Samuli Laine* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2206.00364)] \\\n1 Jun 2022\n\n**On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models** \\\n*Kamil Deja, Anna Kuzina, Tomasz Trzciński, Jakub M. Tomczak* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2206.00070)] \\\n31 May 2022\n\n**Few-Shot Diffusion Models** \\\n*Giorgio Giannone, Didrik Nielsen, Ole Winther* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2205.15463)] \\\n30 May 2022\n\n**A Continuous Time Framework for Discrete Denoising Models** \\\n*Andrew Campbell, Joe Benton, Valentin De Bortoli, Tom Rainforth, George Deligiannidis, Arnaud Doucet* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2205.14987)] \\\n30 May 2022\n\n**Maximum Likelihood Training of Implicit Nonlinear Diffusion Models** \\\n*Dongjun Kim, Byeonghu Na, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, Il-Chul Moon* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2205.13699)] \\\n27 May 2022\n\n**Accelerating Diffusion Models via Early Stop of the Diffusion Process** \\\n*Zhaoyang Lyu, Xudong XU, Ceyuan Yang, Dahua Lin, Bo Dai* \\\nICML 2022. [[Paper](https://arxiv.org/abs/2205.12524)] \\\n25 May 2022\n\n\n\n**Flexible Diffusion Modeling of Long Videos** \\\n*William Harvey, Saeid Naderiparizi, Vaden Masrani, Christian Weilbach, Frank Wood* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2205.11495)] [[Github](https://github.com/plai-group/flexible-video-diffusion-modeling)] \\\n23 May 2022\n\n**MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation** \\\n*Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2205.09853)] [[Github](https://github.com/voletiv/mcvd-pytorch)] \\\n19 May 2022\n\n**On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models** \\\n*Vedant Singh, Surgan Jandial, Ayush Chopra, Siddharth Ramesh, Balaji Krishnamurthy, Vineeth N. Balasubramanian* \\\nCVPR Workshop 2022. [[Paper](https://arxiv.org/abs/2205.03859)] \\\n8 May 2022\n\n**Subspace Diffusion Generative Models** \\\n*Bowen Jing, Gabriele Corso, Renato Berlinghieri, Tommi Jaakkola* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2205.01490)] [[Github](https://github.com/bjing2016/subspace-diffusion)] \\\n3 May 2022\n\n**Fast Sampling of Diffusion Models with Exponential Integrator** \\\n*Qinsheng Zhang, Yongxin Chen* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2204.13902)] \\\n29 Apr 2022\n\n**Semi-Parametric Neural Image Synthesis** \\\n*Andreas Blattmann, Robin Rombach, Kaan Oktay, Jonas Müller, Björn Ommer* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2204.11824)] \\\n25 Apr 2022\n\n\n**Video Diffusion Models** \\\n*Jonathan Ho, Tim Salimans, Alexey Gritsenko, William Chan, Mohammad Norouzi, David J. Fleet* \\\nNeurIPS 2022. [[Paper](https://arxiv.org/abs/2204.03458)] \\\n7 Apr 2022\n\n**Perception Prioritized Training of Diffusion Models** \\\n*Jooyoung Choi, Jungbeom Lee, Chaehun Shin, Sungwon Kim, Hyunwoo Kim, Sungroh Yoon* \\\nCVPR 2022. [[Paper](https://arxiv.org/abs/2204.00227)] [[Github](https://github.com/jychoi118/P2-weighting)] \\\n1 Apr 2022\n\n**Generating High Fidelity Data from Low-density Regions using Diffusion Models** \\\n*Vikash Sehwag, Caner Hazirbas, Albert Gordo, Firat Ozgenel, Cristian Canton Ferrer* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2203.17260)] \\\n31 Mar 2022\n\n**Diffusion Models for Counterfactual Explanations** \\\n*Guillaume Jeanneret, Loïc Simon, Frédéric Jurie* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2203.15636)] \\\n29 Mar 2022\n\n**Denoising Likelihood Score Matching for Conditional Score-based Data Generation** \\\n*Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Yi-Chen Lo, Chia-Che Chang, Yu-Lun Liu, Yu-Lin Chang, Chia-Ping Chen, Chun-Yi Lee* \\\nICLR 2022. [[Paper](https://arxiv.org/abs/2203.14206)] \\\n27 Mar 2022\n\n**Diffusion Probabilistic Modeling for Video Generation** \\\n*Ruihan Yang, Prakhar Srivastava, Stephan Mandt* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2203.09481)] [[Github](https://github.com/buggyyang/rvd)] \\\n16 Mar 2022\n\n**Dynamic Dual-Output Diffusion Models** \\\n*Yaniv Benny, Lior Wolf* \\\nCVPR 2022. [[Paper](https://arxiv.org/abs/2203.04304)] \\\n8 Mar 2022\n\n**Conditional Simulation Using Diffusion Schrödinger Bridges** \\\n*Yuyang Shi, Valentin De Bortoli, George Deligiannidis, Arnaud Doucet* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2202.13460)] \\\n27 Feb 2022\n\n**Diffusion Causal Models for Counterfactual Estimation** \\\n*Pedro Sanchez, Sotirios A. Tsaftaris* \\\nPMLR 2022. [[Paper](https://arxiv.org/abs/2202.10166)] \\\n21 Feb 2022\n\n**Pseudo Numerical Methods for Diffusion Models on Manifolds** \\\n*Luping Liu, Yi Ren, Zhijie Lin, Zhou Zhao* \\\nICLR 2022. [[Paper](https://arxiv.org/abs/2202.09778)] [[Github](https://github.com/luping-liu/PNDM)] \\\n20 Feb 2022\n\n**Truncated Diffusion Probabilistic Models** \\\n*Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2202.09671)] \\\n19 Feb 2022\n\n**Understanding DDPM Latent Codes Through Optimal Transport** \\\n*Valentin Khrulkov, Ivan Oseledets* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2202.07477)] \\\n14 Feb 2022\n\n**Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality** \\\n*Daniel Watson, William Chan, Jonathan Ho, Mohammad Norouzi* \\\nICLR 2022. [[Paper](https://arxiv.org/abs/2202.05830)] \\\n11 Feb 2022\n\n\n**Diffusion bridges vector quantized Variational AutoEncoders** \\\n*Max Cohen, Guillaume Quispe, Sylvain Le Corff, Charles Ollion, Eric Moulines* \\\nICML 2022. [[Paper](https://arxiv.org/abs/2202.04895)] \\\n10 Feb 2022\n\n**Progressive Distillation for Fast Sampling of Diffusion Models** \\\n*Tim Salimans, Jonathan Ho* \\\nICLR 2022. [[Paper](https://arxiv.org/abs/2202.00512)] \\\n1 Feb 2022\n\n**Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models** \\\n*Fan Bao, Chongxuan Li, Jun Zhu, Bo Zhang* \\\nICLR 2022. [[Paper](https://arxiv.org/abs/2201.06503)] \\\n17 Jan 2022\n\n**DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents** \\\n*Kushagra Pandey, Avideep Mukherjee, Piyush Rai, Abhishek Kumar* \\\narXiv 2022. [[Paper](https://arxiv.org/abs/2201.00308)] [[Github](https://github.com/kpandey008/DiffuseVAE)] \\\n2 Jan 2022\n\n**Itô-Taylor Sampling Scheme for Denoising Diffusion Probabilistic Models using Ideal Derivatives** \\\n*Hideyuki Tachibana, Mocho Go, Muneyoshi Inahara, Yotaro Katayama, Yotaro Watanabe* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2112.13339)] \\\n26 Dec 2021\n\n**GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models** \\\n*Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, Mark Chen* \\\nICML 2021. [[Paper](https://arxiv.org/abs/2112.10741)] [[Github](https://github.com/openai/glide-text2im)] \\\n20 Dec 2021\n\n**High-Resolution Image Synthesis with Latent Diffusion Models** \\\n*Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2112.10752)] [[Github](https://github.com/CompVis/latent-diffusion)] \\\n20 Dec 2021\n\n**Heavy-tailed denoising score matching** \\\n*Jacob Deasy, Nikola Simidjievski, Pietro Liò* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2112.09788)] \\\n17 Dec 2021\n\n**High Fidelity Visualization of What Your Self-Supervised Representation Knows About** \\\n*Florian Bordes, Randall Balestriero, Pascal Vincent* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2112.09164)] \\\n16 Dec 2021\n\n**Tackling the Generative Learning Trilemma with Denoising Diffusion GANs** \\\n*Zhisheng Xiao, Karsten Kreis, Arash Vahdat* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2112.07804)] [[Project](https://nvlabs.github.io/denoising-diffusion-gan)] \\\n15 Dec 2021\n\n**Score-Based Generative Modeling with Critically-Damped Langevin Diffusion** \\\n*Tim Dockhorn, Arash Vahdat, Karsten Kreis* \\\nICLR 2022. [[Paper](https://arxiv.org/abs/2112.07068)] [[Project](https://nv-tlabs.github.io/CLD-SGM/)] \\\n14 Dec 2021\n\n**More Control for Free! Image Synthesis with Semantic Diffusion Guidance** \\\n*Xihui Liu, Dong Huk Park, Samaneh Azadi, Gong Zhang, Arman Chopikyan, Yuxiao Hu, Humphrey Shi, Anna Rohrbach, Trevor Darrell* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2112.05744)] \\\n10 Dec 2021\n\n**Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation** \\\n*Minghui Hu, Yujie Wang, Tat-Jen Cham, Jianfei Yang, P.N.Suganthan* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2112.01799)] \\\n3 Dec 2021\n\n**Diffusion Autoencoders: Toward a Meaningful and Decodable Representation** \\\n*Konpat Preechakul, Nattanat Chatthee, Suttisak Wizadwongsa, Supasorn Suwajanakorn* \\\nCVPR 2022. [[Paper](https://arxiv.org/abs/2111.15640)] [[Project](https://diff-ae.github.io/)] [[Github](https://github.com/phizaz/diffae)] \\\n30 Dec 2021\n\n**Conditional Image Generation with Score-Based Diffusion Models** \\\n*Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb, Christian Etmann* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2111.13606)] \\\n26 Nov 2021\n\n**Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes** \\\n*Sam Bond-Taylor, Peter Hessey, Hiroshi Sasaki, Toby P. Breckon, Chris G. Willcocks* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2111.12701)] [[Github](https://github.com/samb-t/unleashing-transformers)] \\\n24 Nov 2021\n\n**Diffusion Normalizing Flow** \\\n*Qinsheng Zhang, Yongxin Chen* \\\nNeurIPS 2021. [[Paper](https://arxiv.org/abs/2110.07579)] [[Github](https://github.com/qsh-zh/DiffFlow)] \\\n14 Oct 2021\n\n**Denoising Diffusion Gamma Models** \\\n*Eliya Nachmani, Robin San Roman, Lior Wolf* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2110.05948)] \\\n10 Oct 2021\n\n**Score-based Generative Neural Networks for Large-Scale Optimal Transport** \\\n*Max Daniels, Tyler Maunu, Paul Hand* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2110.03237)] \\\n7 Oct 2021\n\n**Score-Based Generative Classifiers** \\\n*Roland S. Zimmermann, Lukas Schott, Yang Song, Benjamin A. Dunn, David A. Klindt* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2110.00473)] \\\n1 Oct 2021\n\n**Classifier-Free Diffusion Guidance** \\\n*Jonathan Ho, Tim Salimans* \\\nNeurIPS Workshop 2021. [[Paper](https://arxiv.org/abs/2207.12598)] \\\n28 Sep 2021\n\n\n**Bilateral Denoising Diffusion Models** \\\n*Max W. Y. Lam, Jun Wang, Rongjie Huang, Dan Su, Dong Yu* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2108.11514)] [[Project](https://bilateral-denoising-diffusion-model.github.io)] \\\n26 Aug 2021\n\n**ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis** \\\n*Patrick Esser, Robin Rombach, Andreas Blattmann, Björn Ommer* \\\nNeurIPS 2021. [[Paper](https://arxiv.org/abs/2108.08827)] [[Project](https://compvis.github.io/imagebart/)] \\\n19 Aug 2021\n\n**ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models** \\\n*Jooyoung Choi, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon, Sungroh Yoon* \\\nICCV 2021 (Oral). [[Paper](https://arxiv.org/abs/2108.02938)] [[Github](https://github.com/jychoi118/ilvr_adm)] \\\n6 Aug 2021\n\n**SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations** \\\n*Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, Stefano Ermon* \\\nICLR  2022. [[Paper](https://arxiv.org/abs/2108.01073)] [[Project](https://sde-image-editing.github.io/)] [[Github](https://github.com/ermongroup/SDEdit)] \\\n2 Aug 2021\n\n**Structured Denoising Diffusion Models in Discrete State-Spaces** \\\n*Jacob Austin, Daniel D. Johnson, Jonathan Ho, Daniel Tarlow, Rianne van den Berg* \\\nNeurIPS 2021. [[Paper](https://arxiv.org/abs/2107.03006)] \\\n7 Jul 2021 \n\n**Variational Diffusion Models** \\\n*Diederik P. Kingma, Tim Salimans, Ben Poole, Jonathan Ho* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2107.00630)] [[Github](https://github.com/google-research/vdm)] \\\n1 Jul 2021 \n\n**Diffusion Priors In Variational Autoencoders** \\\n*Antoine Wehenkel, Gilles Louppe* \\\nICML Workshop 2021. [[Paper](https://arxiv.org/abs/2106.15671)] \\\n29 Jun 2021\n\n**Deep Generative Learning via Schrödinger Bridge** \\\n*Gefei Wang, Yuling Jiao, Qian Xu, Yang Wang, Can Yang* \\\nICML 2021. [[Paper](https://arxiv.org/abs/2106.10410)] \\\n19 Jun 2021\n\n**Non Gaussian Denoising Diffusion Models** \\\n*Eliya Nachmani, Robin San Roman, Lior Wolf* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2106.07582)] [[Project](https://enk100.github.io/Non-Gaussian-Denoising-Diffusion-Models/)] \\\n14 Jun 2021 \n\n**D2C: Diffusion-Denoising Models for Few-shot Conditional Generation** \\\n*Abhishek Sinha, Jiaming Song, Chenlin Meng, Stefano Ermon* \\\nNeurIPS 2021. [[Paper](https://arxiv.org/abs/2106.06819)] [[Project](https://d2c-model.github.io/)] [[Github](https://github.com/d2c-model/d2c-model.github.io)] \\\n12 Jun 2021\n\n**Score-based Generative Modeling in Latent Space** \\\n*Arash Vahdat, Karsten Kreis, Jan Kautz* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2106.05931)] \\\n10 Jun 2021\n\n**Learning to Efficiently Sample from Diffusion Probabilistic Models** \\\n*Daniel Watson, Jonathan Ho, Mohammad Norouzi, William Chan* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2106.03802)] \\\n7 Jun 2021 \n\n**A Variational Perspective on Diffusion-Based Generative Models and Score Matching** \\\n*Chin-Wei Huang, Jae Hyun Lim, Aaron Courville* \\\nNeurIPS 2021. [[Paper](https://arxiv.org/abs/2106.02808)] [[Github](https://github.com/CW-Huang/sdeflow-light)] \\\n5 Jun 2021 \n\n**Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation** \\\n*Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon* \\\nICML 2022. [[Paper](https://arxiv.org/abs/2106.05527)] \\\n10 Jun 2021\n\n**Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling** \\\n*Valentin De Bortoli, James Thornton, Jeremy Heng, Arnaud Doucet* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2106.01357)] [[Project](https://jtt94.github.io/papers/schrodinger_bridge)] [[Github](https://github.com/JTT94/diffusion_schrodinger_bridge)] \\\n1 Jun 2021\n\n**On Fast Sampling of Diffusion Probabilistic Models** \\\n*Zhifeng Kong, Wei Ping* \\\nICML Workshop 2021. [[Paper](https://arxiv.org/abs/2106.00132)] [[Github](https://github.com/FengNiMa/FastDPM_pytorch)] \\\n31 May 2021 \n\n**Cascaded Diffusion Models for High Fidelity Image Generation** \\\n*Jonathan Ho, Chitwan Saharia, William Chan, David J. Fleet, Mohammad Norouzi, Tim Salimans* \\\nJMLR 2021. [[Paper](https://arxiv.org/abs/2106.15282)] [[Project](https://cascaded-diffusion.github.io/)] \\\n30 May 2021 \n\n**Gotta Go Fast When Generating Data with Score-Based Models** \\\n*Alexia Jolicoeur-Martineau, Ke Li, Rémi Piché-Taillefer, Tal Kachman, Ioannis Mitliagkas* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2105.14080)] [[Github](https://github.com/AlexiaJM/score_sde_fast_sampling)] \\\n28 May 2021\n\n**Diffusion Models Beat GANs on Image Synthesis** \\\n*Prafulla Dhariwal, Alex Nichol* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2105.05233)] [[Github](https://github.com/openai/guided-diffusion)] \\\n11 May 2021 \n\n**Image Super-Resolution via Iterative Refinement** \\\n*Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J. Fleet, Mohammad Norouzi* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2104.07636)] [[Project](https://iterative-refinement.github.io/)] [[Github](https://github.com/Janspiry/Image-Super-Resolution-via-Iterative-Refinement)] \\\n15 Apr 2021 \n\n**Noise Estimation for Generative Diffusion Models** \\\n*Robin San-Roman, Eliya Nachmani, Lior Wolf* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2104.02600)] \\\n6 Apr 2021 \n\n**Improved Denoising Diffusion Probabilistic Models** \\\n*Alex Nichol, Prafulla Dhariwal* \\\nICLR 2021. [[Paper](https://arxiv.org/abs/2102.09672)] [[Github](https://github.com/openai/improved-diffusion)] \\\n18 Feb 2021 \n\n**Maximum Likelihood Training of Score-Based Diffusion Models** \\\n*Yang Song, Conor Durkan, Iain Murray, Stefano Ermon* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2101.09258)] \\\n22 Jan 2021 \n\n**Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed** \\\n*Eric Luhman, Troy Luhman* \\\narXiv 2021. [[Paper](https://arxiv.org/abs/2101.02388)] [[Github](https://github.com/tcl9876/Denoising_Student)] \\\n7 Jan 2021\n\n**Learning Energy-Based Models by Diffusion Recovery Likelihood** \\\n*Ruiqi Gao, Yang Song, Ben Poole, Ying Nian Wu, Diederik P. Kingma* \\\nICLR 2021. [[Paper](https://arxiv.org/abs/2012.08125)] [[Github](https://github.com/ruiqigao/recovery_likelihood)] \\\n15 Dec 2020 \n\n**Score-Based Generative Modeling through Stochastic Differential Equations** \\\n*Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole* \\\nICLR 2021 (Oral). [[Paper](https://arxiv.org/abs/2011.13456)] [[Github](https://github.com/yang-song/score_sde)] \\\n26 Nov 2020 \n\n**Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models** \\\n*Fan Bao, Kun Xu, Chongxuan Li, Lanqing Hong, Jun Zhu, Bo Zhang* \\\nICML 2021. [[Paper](https://arxiv.org/abs/2010.08258)] \\\n16 Oct 2020\n\n**Denoising Diffusion Implicit Models**  \\\n*Jiaming Song, Chenlin Meng, Stefano Ermon* \\\nICLR 2021. [[Paper](https://arxiv.org/abs/2010.02502)] [[Github](https://github.com/ermongroup/ddim)] \\\n6 Oct 2020\n\n**Adversarial score matching and improved sampling for image generation** \\\n*Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Rémi Tachet des Combes, Ioannis Mitliagkas* \\\nICLR 2021. [[Paper](https://arxiv.org/abs/2009.05475)] [[Github](https://github.com/AlexiaJM/AdversarialConsistentScoreMatching)] \\\n11 Sep 2020\n\n**Denoising Diffusion Probabilistic Models** \\\n*Jonathan Ho, Ajay Jain, Pieter Abbeel* \\\nNeurIPS 2020. [[Paper](https://arxiv.org/abs/2006.11239)] [[Github](https://github.com/hojonathanho/diffusion)] [[Github2](https://github.com/pesser/pytorch_diffusion)] \\\n19 Jun 2020 \n\n**Improved Techniques for Training Score-Based Generative Models** \\\n*Yang Song, Stefano Ermon* \\\nNeurIPS 2020. [[Paper](https://arxiv.org/abs/2006.09011)] [[Github](https://github.com/ermongroup/ncsnv2)] \\\n16 Jun 2020 \n\n**Generative Modeling by Estimating Gradients of the Data Distribution** \\\n*Yang Song, Stefano Ermon* \\\nNeurIPS 2019. [[Paper](https://arxiv.org/abs/1907.05600)] [[Project](https://yang-song.github.io/blog/2021/score/)] [[Github](https://github.com/ermongroup/ncsn)] \\\n12 Jul 2019 \n\n**Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit** \\\n*Belinda Tzen, Maxim Raginsky* \\\narXiv 2019. [[Paper](https://arxiv.org/abs/1905.09883)] \\\n23 May 2019 \n\n**Deep Unsupervised Learning using Nonequilibrium Thermodynamics** \\\n*Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan, Surya Ganguli* \\\nICML 2015. [[Paper](https://arxiv.org/abs/1503.03585)] [[Github](https://github.com/Sohl-Dickstein/Diffusion-Probabilistic-Models)] \\\n2 Mar 2015\n\n### Classification\n\n**Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Models** \\\n*Joseph Goodier, Neill D. F. Campbell* \\\nBMVC 2023. [[Paper](https://arxiv.org/abs/2310.17432)] \\\n26 Oct 2023\n\n**Multi-scale Diffusion Denoised Smoothing** \\\n*Jongheon Jeong, Jinwoo Shin* \\\nNeurIPS 2023. [[Paper](https://arxiv.org/abs/2310.16779)] \\\n25 Oct 2023\n\n**DiffRef3D: A Diffusion-based Proposal Refinement Framework for 3D Object Detection** \\\n*Se-Ho Kim, Inyong Koo, Inyoung Lee, Byeongjun Park, Changick Kim* \\\narXiv 2023. [[Paper](https://arxiv.org/abs/2310.16349)] \\\n25 Oct 2023\n\n**Denoising Task Routing for Diffusion Models** \\\n*Byeongjun Park, ","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/diff-usion%2Fawesome-diffusion-models/projects"}