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 7, 2024

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
IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
Shitong Shao, Zikai Zhou, Lichen Bai, Haoyi Xiond, Zeke Xie
Diffusion Model Video Diffusion Model Image Diffusion Model Step Sampling

October 4, 2024

AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models
Artur Kasymov, Marcin Sendera, Michał Stypułkowski, Maciej Zięba, Przemysław Spurek
Diffusion Model Adaptation Concern Conditional Diffusion Model Low Rank Adaptation
ShieldDiff: Suppressing Sexual Content Generation from Diffusion Models through Reinforcement Learning
Dong Han, Salaheldin Mohamed, Yong Li
Reinforcement Learning Diffusion Model Unsafe Image Unsafe Content Complex Reward Function
Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Models
Chumeng Liang, Jiaxuan You
Diffusion Model Membership Inference Attack Pre Trained Diffusion Model Practical Benchmark
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Benyuan Meng, Qianqian Xu, Zitai Wang, Xiaochun Cao, Qingming Huang
Diffusion Model Semantic Segmentation Discriminative Feature Discriminative Task Diffusion Model Architecture Dense Feature
Diffusion State-Guided Projected Gradient for Inverse Problems
Rayhan Zirvi, Bahareh Tolooshams, Anima Anandkumar
Diffusion Model Inverse Problem Diffusion Explainer Natural Gradient Ill Posed Inverse Problem Gradient Projection Diffusion Inverse Solver
Dynamic Diffusion Transformer
Wangbo Zhao, Yizeng Han, Jiasheng Tang, Kai Wang, Yibing Song, Gao Huang, Fan Wang, Yang You
Diffusion Model Image Generation Diffusion Transformer
Latent Abstractions in Generative Diffusion Models
Giulio Franzese, Mattia Martini, Giulio Corallo, Paolo Papotti, Pietro Michiardi
Diffusion Model Generative Model Generative Diffusion Model Generative Process Diffusion Based Generative Model Abstraction Learning
Multi-Robot Motion Planning with Diffusion Models
Yorai Shaoul, Itamar Mishani, Shivam Vats, Jiaoyang Li, Maxim Likhachev
Diffusion Model Multi Robot Multi Robot System Robot Data

October 3, 2024

Revealing the Unseen: Guiding Personalized Diffusion Models to Expose Training Data
Xiaoyu Wu, Jiaru Zhang, Steven Wu
Diffusion Model Fine Tuning Unseen Video
Learning Optimal Control and Dynamical Structure of Global Trajectory Search Problems with Diffusion Models
Jannik Graebner, Anjian Li, Amlan Sinha, Ryne Beeson
Diffusion Model Optimal Policy Trajectory Tracking Trajectory Design Invariant Manifold Restricted Three Body Problem
SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
Hongxiang Zhang, Yifeng He, Hao Chen
Diffusion Model Text to Image Diffusion Model Text to Image Text Conditioned Image Generation
GUD: Generation with Unified Diffusion
Mathis Gerdes, Max Welling, Miranda C. N. Cheng
Diffusion Model Generative Model Faithful Generation Diffusion Explainer Diffusion Based Framework
Diffusion Models are Evolutionary Algorithms
Yanbo Zhang, Benedikt Hartl, Hananel Hazan, Michael Levin
Diffusion Model Evolutionary Algorithm Diffusion Based Method Diffusion Dynamic
Towards a Theoretical Understanding of Memorization in Diffusion Models
Yunhao Chen, Xingjun Ma, Difan Zou, Yu-Gang Jiang
Diffusion Model Theoretical Understanding Generative Artificial Intelligence Probabilistic Model Limited Memorization Data Memorization Unconditional Model

Diffusion Model

Papers

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

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis

AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models

ShieldDiff: Suppressing Sexual Content Generation from Diffusion Models through Reinforcement Learning

Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Models

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

Diffusion State-Guided Projected Gradient for Inverse Problems

Dynamic Diffusion Transformer

Latent Abstractions in Generative Diffusion Models

Multi-Robot Motion Planning with Diffusion Models

Revealing the Unseen: Guiding Personalized Diffusion Models to Expose Training Data

Learning Optimal Control and Dynamical Structure of Global Trajectory Search Problems with Diffusion Models

SteerDiff: Steering towards Safe Text-to-Image Diffusion Models

GUD: Generation with Unified Diffusion

Diffusion Models are Evolutionary Algorithms

Towards a Theoretical Understanding of Memorization in Diffusion Models