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

June 5, 2024

Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models
Lucas Berry, Axel Brando, David Meger
Diffusion Model Conditional Diffusion Model Epistemic Uncertainty Generative Diffusion Model Diffusion Network Uncertainty Mitigation
Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis
Juanhua Zhang, Ruodan Yan, Alessandro Perelli, Xi Chen, Chao Li
Diffusion Model Generative Adversarial Network Diffusion MRI Physic Informed Diffusion Diffusion Image
Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models
Zihan Ye, Shreyank N. Gowda, Xiaobo Jin, Xiaowei Huang, Haotian Xu, Yaochu Jin, Kaizhu Huang
Diffusion Model Generative Model Zero Shot Data Efficiency Generative Zero Shot Learning
TSPDiffuser: Diffusion Models as Learned Samplers for Traveling Salesperson Path Planning Problems
Ryo Yonetani
Diffusion Model Learning Based Collision Free Feasible Path Obstacle Map Geometric Motion Planning

June 4, 2024

ORACLE: Leveraging Mutual Information for Consistent Character Generation with LoRAs in Diffusion Models
Kiymet Akdemir, Pinar Yanardag
Diffusion Model Text to Image Diffusion Model Mutual Information Visual Creation Test Oracle Character Generation charactER Representation
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Enshu Liu, Rui Wan, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang
Diffusion Model Video Generation Diffusion Transformer Accurate Quantization
Guiding a Diffusion Model with a Bad Version of Itself
Tero Karras, Miika Aittala, Tuomas Kynkäänniemi, Jaakko Lehtinen, Timo Aila, Samuli Laine
Diffusion Model Diffusion Based Image Generation Unconditional Diffusion Model Higher Resolution Image Unconditional Model
Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems
Jason Hu, Bowen Song, Xiaojian Xu, Liyue Shen, Jeffrey A. Fessler
Diffusion Model Inverse Problem Image Prior Diffusion Inverse Solver
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch
Diffusion Model Limited Memorization Single Neuron Data Memorization NeMo Team Critical Neuron Memory Deep Learning Memorized Sample
Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
Bálint Máté, François Fleuret, Tristan Bereau
Diffusion Model Molecular Conformation Free Energy Thermodynamic Integration Conformational Ensemble Lennard Jones
The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise
Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Boqing Gong, Cho-Jui Hsieh, Minhao Cheng
Diffusion Model Image Generation Lottery Ticket Hypothesis Object Generation Text to Image Generation Task Initial Noise
Plug-and-Play Diffusion Distillation
Yi-Ting Hsiao, Siavash Khodadadeh, Kevin Duarte, Wei-An Lin, Hui Qu, Mingi Kwon, Ratheesh Kalarot
Diffusion Model Text to Image Model Lightweight Model Latent Space Diffusion
Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
Wenzhuo Tang, Haitao Mao, Danial Dervovic, Ivan Brugere, Saumitra Mishra, Yuying Xie, Jiliang Tang
Diffusion Model Pre Trained Diffusion Model Graph Augmentation

June 3, 2024

Diffusion Boosted Trees
Xizewen Han, Mingyuan Zhou
Diffusion Model Decision Tree Diffusion Explainer Tree Specie Gradient Boosting Boosting Algorithm Boosted Tree
ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
Guanxing Lu, Zifeng Gao, Tianxing Chen, Wenxun Dai, Ziwei Wang, Yansong Tang
Diffusion Model Action Space Robotic Manipulation Manipulation Task Consistency Model Diffusion Based Method
Differentially Private Fine-Tuning of Diffusion Models
Yu-Lin Tsai, Yizhe Li, Zekai Chen, Po-Yu Chen, Chia-Mu Yu, Xuebin Ren, Francois Buet-Golfouse
Diffusion Model Differential Privacy Differential Privacy SGD Privacy Utility Trade Private Fine Tuning
$\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, Tao Chen
Diffusion Model Image Generation Diffusion Transformer Acceleration Method
Layout Agnostic Scene Text Image Synthesis with Diffusion Models
Qilong Zhangli, Jindong Jiang, Di Liu, Licheng Yu, Xiaoliang Dai, Ankit Ramchandani, Guan Pang, Dimitris N. Metaxas, Praveen Krishnan
Diffusion Model Image Generation Character Image Feature Encoder Scene Text Generation
Constraint-Aware Diffusion Models for Trajectory Optimization
Anjian Li, Zihan Ding, Adji Bousso Dieng, Ryne Beeson
Diffusion Model Trajectory Optimization Trajectory Optimization Problem Hybrid Loss
Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
Shivam Gupta, Linda Cai, Sitan Chen
Diffusion Model Sequential Information Diffusion Sampling Parallel Sampling Log Concave Sampling Discretization Method Randomized Midpoint

Diffusion Model

Papers

Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models

Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis

Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models

TSPDiffuser: Diffusion Models as Learned Samplers for Traveling Salesperson Path Planning Problems

ORACLE: Leveraging Mutual Information for Consistent Character Generation with LoRAs in Diffusion Models

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Guiding a Diffusion Model with a Bad Version of Itself

Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models

Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise

Plug-and-Play Diffusion Distillation

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

Diffusion Boosted Trees

ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation

Differentially Private Fine-Tuning of Diffusion Models

$\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers

Layout Agnostic Scene Text Image Synthesis with Diffusion Models

Constraint-Aware Diffusion Models for Trajectory Optimization

Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel