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 9, 2024

Decouple-Then-Merge: Towards Better Training for Diffusion Models
Qianli Ma, Xuefei Ning, Dongrui Liu, Li Niu, Linfeng Zhang
Diffusion Model Image Generation Stable Diffusion Improved Training Denoising Task
BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
Fangyikang Wang, Hubery Yin, Yuejiang Dong, Huminhao Zhu, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li
Diffusion Model Fast Sampling Inversion Performance Diffusion Posterior Sampling Iterative Inversion
G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving
Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji
Diffusion Model Inverse Problem Discrete Diffusion Model Diffusion Based Method Discrete Diffusion
Chemistry-Inspired Diffusion with Non-Differentiable Guidance
Yuchen Shen, Chenhao Zhang, Sijie Fu, Chenghui Zhou, Newell Washburn, Barnabás Póczos
Diffusion Model Conditional Diffusion Model Quantum Chemistry Robust Guidance Unconditional Diffusion Model

October 8, 2024

Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
Sha Guo, Zhuo Chen, Yang Zhao, Ning Zhang, Xiaotong Li, Lingyu Duan
Diffusion Model Image Compression Diffusion Probabilistic Model Diffusion Based Feature Compression
Sparse Repellency for Shielded Generation in Text-to-image Diffusion Models
Michael Kirchhof, James Thornton, Pierre Ablin, Louis Béthune, Eugene Ndiaye, Marco Cuturi
Diffusion Model Text to Image Diffusion Model Text to Image Generation Random Walk Diversity Regularizer Shield Synthesis
TIMBA: Time series Imputation with Bi-directional Mamba Blocks and Diffusion models
Javier Solís-García, Belén Vega-Márquez, Juan A. Nepomuceno, Isabel A. Nepomuceno-Chamorro
Diffusion Model Recurrent Neural Network Mamba Based Spatiotemporal Representation Time Series Imputation Time Transformer
Training-free Diffusion Model Alignment with Sampling Demons
Po-Hung Yeh, Kuang-Huei Lee, Jun-Cheng Chen
Diffusion Model Text to Image Generation Visual Language Model Preference Alignment Differentiable Reward Diffusion Alignment
TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation
Gihyun Kwon, Jong Chul Ye
Diffusion Model Video Generation Video Generation Model Diffusion Sampling Diffusion Generated Image Multi Concept Composition

October 7, 2024

Continuous Ensemble Weather Forecasting with Diffusion models
Martin Andrae, Tomas Landelius, Joel Oskarsson, Fredrik Lindsten
Diffusion Model Ensemble Forecast Many Trajectory Ensemble Weather Deterministic Forecast
SePPO: Semi-Policy Preference Optimization for Diffusion Alignment
Daoan Zhang, Guangchen Lan, Dong-Jun Han, Wenlin Yao, Xiaoman Pan, Hongming Zhang, Mingxiao Li, Pengcheng Chen, Yu Dong, Christopher Brinton, Jiebo Luo
Reinforcement Learning Diffusion Model Reward Model Diffusion Alignment
DiffuseReg: Denoising Diffusion Model for Obtaining Deformation Fields in Unsupervised Deformable Image Registration
Yongtai Zhuo, Yiqing Shen
Diffusion Model Image Registration Deformable Image Registration Deformation Field Rigid Registration Iterative Denoising Registration Model
Leveraging Multimodal Diffusion Models to Accelerate Imaging with Side Information
Timofey Efimov, Harry Dong, Megna Shah, Jeff Simmons, Sean Donegan, Yuejie Chi
Diffusion Model Image Reconstruction Accelerated MRI Reconstruction Side Information
Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning
Ayano Hiranaka, Shang-Fu Chen, Chieh-Hsin Lai, Dongjun Kim, Naoki Murata, Takashi Shibuya, Wei-Hsiang Liao, Shao-Hua Sun, Yuki Mitsufuji
Reinforcement Learning Diffusion Model Human Feedback Reward Model Reinforcement Learning From Human Feedback Controllable Generation Adversarial Feedback
Low-Rank Continual Personalization of Diffusion Models
Łukasz Staniszewski, Katarzyna Zaleska, Kamil Deja
Diffusion Model Catastrophic Forgetting Continual Learning Scenario Continual Fine Tuning Large Diffusion Model
FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
Haokun Chen, Hang Li, Yao Zhang, Gengyuan Zhang, Jinhe Bi, Philip Torr, Jindong Gu, Denis Krompass, Volker Tresp
Diffusion Model Latent Diffusion Model Heterogeneous Setting One Shot Federated Learning Client Data Heterogeneity
Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models
Yuchen Wu, Yuxin Chen, Yuting Wei
Diffusion Model Generative Model Diffusion Sampling Anderson Acceleration Diffusion Sampler
Diffusion Models in 3D Vision: A Survey
Zhen Wang, Dongyuan Li, Renhe Jiang
Diffusion Model Timely Survey 3D Object Generation Real World 3D

October 5, 2024

Compositional Diffusion Models for Powered Descent Trajectory Generation with Flexible Constraints
Julia Briden, Yilun Du, Enrico M. Zucchelli, Richard Linares
Diffusion Model Optimal Trajectory Temporal Trajectory Long Horizon Planning Trajectory Generator Powered Descent Guidance
Accelerating Diffusion Models with One-to-Many Knowledge Distillation
Linfeng Zhang, Kaisheng Ma
Diffusion Model Logit Distillation

Diffusion Model

Papers

Decouple-Then-Merge: Towards Better Training for Diffusion Models

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models

G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving

Chemistry-Inspired Diffusion with Non-Differentiable Guidance

Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach

Sparse Repellency for Shielded Generation in Text-to-image Diffusion Models

TIMBA: Time series Imputation with Bi-directional Mamba Blocks and Diffusion models

Training-free Diffusion Model Alignment with Sampling Demons

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

Continuous Ensemble Weather Forecasting with Diffusion models

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment

DiffuseReg: Denoising Diffusion Model for Obtaining Deformation Fields in Unsupervised Deformable Image Registration

Leveraging Multimodal Diffusion Models to Accelerate Imaging with Side Information

Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

Low-Rank Continual Personalization of Diffusion Models

FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models

Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models

Diffusion Models in 3D Vision: A Survey

Compositional Diffusion Models for Powered Descent Trajectory Generation with Flexible Constraints

Accelerating Diffusion Models with One-to-Many Knowledge Distillation