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

October 18, 2024

Dynamic Negative Guidance of Diffusion Models
Felix Koulischer, Johannes Deleu, Gabriel Raya, Thomas Demeester, Luca Ambrogioni
Diffusion Model Generative Process Negative Sentiment Negative Prompt
Mitigating Embedding Collapse in Diffusion Models for Categorical Data
Bac Nguyen, and Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Stefano Ermon, Yuki Mitsufuji
Diffusion Model Latent Diffusion Model Categorical Data Event Collapse Diffusion Embeddings
ERDDCI: Exact Reversible Diffusion via Dual-Chain Inversion for High-Quality Image Editing
Jimin Dai, Yingzhen Zhang, Shuo Chen, Jian Yang, Lei Luo
Diffusion Model High Quality Image Inversion Performance Reversible Dynamic
Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers
Runjia Li, Qiwei Di, Quanquan Gu
Diffusion Model Convergence Analysis Score Based Diffusion Model Fast Sampling Stochastic Sampling Deterministic Sampling
Assessing Open-world Forgetting in Generative Image Model Customization
Héctor Laria, Alex Gomez-Villa, Imad Eddine Marouf, Kai Wang, Bogdan Raducanu, Joost van de Weijer
Diffusion Model Text to Image Anti Forgetting Zero Shot Classification Semantic Change

October 17, 2024

MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks
Xinxin Liu, Zhongliang Guo, Siyuan Huang, Chun Pong Lau
Diffusion Model Adversarial Attack Adversarial Example Adversarial Perturbation Gradient Based Adversarial Multimodal Attack
On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow
Tonghan Wang, Heng Dong, Yanchen Jiang, David C. Parkes, Milind Tambe
Diffusion Model Partial Observability Error Bound General Flow New Attractor POMDP Policy
Influence Functions for Scalable Data Attribution in Diffusion Models
Bruno Mlodozeniec, Runa Eschenhagen, Juhan Bae, Alexander Immer, David Krueger, Richard Turner
Diffusion Model External Influence Influence Function
Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation
Da Long, Zhitong Xu, Guang Yang, Akil Narayan, Shandian Zhe
Diffusion Model Surrogate Model Denoising Diffusion Probabilistic Model Probabilistic Surrogate Multi Physic Basic Emulator Multi Physic Simulation
Probing the Latent Hierarchical Structure of Data via Diffusion Models
Antonio Sclocchi, Alessandro Favero, Noam Itzhak Levi, Matthieu Wyart
Diffusion Model Raw Data Latent Variable Latent Structure Diffusion Based Model Latent Hierarchy Latent Shift
Improved Convergence Rate for Diffusion Probabilistic Models
Gen Li, Yuchen Jiao
Diffusion Model Convergence Rate Diffusion Probabilistic Model Score Based Diffusion Model Iteration Complexity Score Estimation Log Concave Sampling
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
Yijun Liang, Shweta Bhardwaj, Tianyi Zhou
Diffusion Model Curriculum Learning Long Tailed Image Guidance
Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
Chenyu Wang, Masatoshi Uehara, Yichun He, Amy Wang, Tommaso Biancalani, Avantika Lal, Tommi Jaakkola, Sergey Levine, Hanchen Wang, Aviv Regev
Diffusion Model Financial Application Reward Model Conditional Diffusion Model Protein Design Reward Maximization Discrete Diffusion Model DNA Related Bioinformatics Domain
L3DG: Latent 3D Gaussian Diffusion
Barbara Roessle, Norman Müller, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder, Angela Dai, Matthias Nießner
Diffusion Model 3D Gaussian 3D Generative
Solving Prior Distribution Mismatch in Diffusion Models via Optimal Transport
Zhanpeng Wang, Shenghao Li, Chen Wang, Shuting Cao, Na Lei, Zhongxuan Luo
Diffusion Model Transportation System Discrete Distribution Early Termination
MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models
Donghao Zhou, Jiancheng Huang, Jinbin Bai, Jiaze Wang, Hao Chen, Guangyong Chen, Xiaowei Hu, Pheng-Ann Heng
Diffusion Model Text to Image Visual Concept Visual Semantics Scalable Personalization
DiffImp: Efficient Diffusion Model for Probabilistic Time Series Imputation with Bidirectional Mamba Backbone
Hongfan Gao, Wangmeng Shen, Xiangfei Qiu, Ronghui Xu, Jilin Hu, Bin Yang
Diffusion Model Mamba Based Time Series Imputation Knowledge Enhanced Conditional Imputation Probabilistic Time Series Forecasting
FDF: Flexible Decoupled Framework for Time Series Forecasting with Conditional Denoising and Polynomial Modeling
Jintao Zhang, Mingyue Cheng, Xiaoyu Tao, Zhiding Liu, Daoyu Wang
Diffusion Model Time Series Forecasting Forecasting Performance Trend Filtering
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
Jiwan Hur, Dong-Jae Lee, Gyojin Han, Jaehyun Choi, Yunho Jeon, Junmo Kim
Diffusion Model Generative Model Critical Synthesis Unlocking Insight Masked Generative Self Generated

October 16, 2024

Geometric Trajectory Diffusion Models
Jiaqi Han, Minkai Xu, Aaron Lou, Haotian Ye, Stefano Ermon
Diffusion Model Generative Model Trajectory Model

Diffusion Model

Papers

Dynamic Negative Guidance of Diffusion Models

Mitigating Embedding Collapse in Diffusion Models for Categorical Data

ERDDCI: Exact Reversible Diffusion via Dual-Chain Inversion for High-Quality Image Editing

Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers

Assessing Open-world Forgetting in Generative Image Model Customization

MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks

On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow

Influence Functions for Scalable Data Attribution in Diffusion Models

Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation

Probing the Latent Hierarchical Structure of Data via Diffusion Models

Improved Convergence Rate for Diffusion Probabilistic Models

Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design

L3DG: Latent 3D Gaussian Diffusion

Solving Prior Distribution Mismatch in Diffusion Models via Optimal Transport

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

DiffImp: Efficient Diffusion Model for Probabilistic Time Series Imputation with Bidirectional Mamba Backbone

FDF: Flexible Decoupled Framework for Time Series Forecasting with Conditional Denoising and Polynomial Modeling

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance

Geometric Trajectory Diffusion Models