Diffusion Model

Diffusion models are generative models that create data by reversing a noise-diffusion process, aiming to generate high-quality samples from complex distributions. Current research focuses on improving efficiency through techniques like stochastic Runge-Kutta methods and dynamic model architectures (e.g., Dynamic Diffusion Transformer), as well as enhancing controllability and safety via methods such as classifier-free guidance and reinforcement learning from human feedback. These advancements are significantly impacting various fields, including medical imaging, robotics, and artistic creation, by enabling novel applications in image generation, inverse problem solving, and multi-modal data synthesis.

Papers

May 24, 2024

CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models
Juan Miguel Lopez Alcaraz, Nils Strodthoff
Diffusion Model Causal Effect Time Series Classification Causal Relationship Attribution Method Causal Attribution Causal Concept
Reducing the cost of posterior sampling in linear inverse problems via task-dependent score learning
Fabian Schneider, Duc-Lam Duong, Matti Lassas, Maarten V. de Hoop, Tapio Helin
Diffusion Model Hidden CoST Posterior Sampling Score Based Linear Inverse Problem Bayesian Inverse Problem Scoring Task
Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2
Yeqing Lin, Minji Lee, Zhao Zhang, Mohammed AlQuraishi
Diffusion Model Product Design Visual Analogue Scale Protein Design Molecular Scaffold
Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
Mingyang Yi, Aoxue Li, Yi Xin, Zhenguo Li
Diffusion Model Text to Image Diffusion Model Latent Diffusion Model Diffusion Based Image Generation Working Mechanism
Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
Yongliang Wu, Shiji Zhou, Mingzhuo Yang, Lianzhe Wang, Heng Chang, Wenbo Zhu, Xinting Hu, Xiao Zhou, Xu Yang
Diffusion Model Text to Image Diffusion Model Machine Unlearning Unlearning Framework Concept Erasure
ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model
Chengming Xu, Kai Hu, Qilin Wang, Donghao Luo, Jiangning Zhang, Xiaobin Hu, Yanwei Fu, Chengjie Wang
Diffusion Model Style Representation Reference Image Stylized Image Generation
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, Sijia Liu
Diffusion Model Adversarial Training Unlearning Framework Harmful Unlearning Robust Unlearning
DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception
Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Xiaobo Xia, Tongliang Liu, Min Yang, Binyuan Hui
Diffusion Model Large Multimodal Model Visual Perception Model Hallucination Image Encoder Character Eye Multimodal Comprehension
NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation
Vikas Thamizharasan, Difan Liu, Matthew Fisher, Nanxuan Zhao, Evangelos Kalogerakis, Michal Lukac
Diffusion Model Vector Representation Vector Graphic Neural Implicit Field Tongue Twister
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
Jingyuan Zhu, Shiyu Li, Yuxuan Liu, Ping Huang, Jiulong Shan, Huimin Ma, Jian Yuan
Diffusion Model Pre Trained Diffusion Model Detection Task Diffusion Generated Image
FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing
Kai Huang, Haoming Wang, Wei Gao
Diffusion Model Text to Image Diffusion Model Pre Trained Diffusion Model Modality Freezing

May 23, 2024

AdjointDEIS: Efficient Gradients for Diffusion Models
Zander W. Blasingame, Chen Liu
Diffusion Model Diffusion SDE Efficient Gradient
SFDDM: Single-fold Distillation for Diffusion models
Chi Hong, Jiyue Huang, Robert Birke, Dick Epema, Stefanie Roos, Lydia Y. Chen
Diffusion Model Teacher Student Distillation High Quality Synthesis
Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
Gen Li, Yuling Yan
Diffusion Model Denoising Diffusion Probabilistic Model Low Dimensional Manifold Score Based Diffusion Model Low Dimensional Structure
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon
Diffusion Model Stable Diffusion Low Resolution Synchronous Generator Diffusion Autoencoder Left Leaning Autoencoder Framework
Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generation
Hongxu Jiang, Muhammad Imran, Linhai Ma, Teng Zhang, Yuyin Zhou, Muxuan Liang, Kuang Gong, Wei Shao
Diffusion Model Image Denoising Denoising Diffusion Image Denoiser Medical Image Generation
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
Shengfang Zhai, Huanran Chen, Yinpeng Dong, Jiajun Li, Qingni Shen, Yansong Gao, Hang Su, Yang Liu
Diffusion Model Data Augmentation Text to Image Diffusion Model Membership Inference
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Zhicheng Sun, Zhenhao Yang, Yang Jin, Haozhe Chi, Kun Xu, Kun Xu, Liwei Chen, Hao Jiang, Yang Song, Kun Gai, Yadong Mu
Diffusion Model Synchronous Generator Flow Mood Personalization Performance Identity Preservation Personalized Image Generation Identity Preserving
Multistable Shape from Shading Emerges from Patch Diffusion
Xinran Nicole Han, Todd Zickler, Ko Nishino
Diffusion Model Synthetic Image Monocular 3D Shading Model Bistable Image
Adversarial Schrödinger Bridge Matching
Nikita Gushchin, Daniil Selikhanovych, Sergei Kholkin, Evgeny Burnaev, Alexander Korotin
Diffusion Model C Gan Denoising Diffusion Schr\"odinger Bridge

Diffusion Model

Papers

CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models

Reducing the cost of posterior sampling in linear inverse problems via task-dependent score learning

Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2

Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient

ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models

DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception

NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation

ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models

FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing

AdjointDEIS: Efficient Gradients for Diffusion Models

SFDDM: Single-fold Distillation for Diffusion models

Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models

PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher

Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generation

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

Multistable Shape from Shading Emerges from Patch Diffusion

Adversarial Schrödinger Bridge Matching