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.
2251papers
Papers - Page 23
December 20, 2024
Differentially Private Federated Learning of Diffusion Models for Synthetic Tabular Data Generation
Semi-Supervised Adaptation of Diffusion Models for Handwritten Text Generation
PromptLA: Towards Integrity Verification of Black-box Text-to-Image Diffusion Models
ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model
December 19, 2024
Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
Diffusion priors for Bayesian 3D reconstruction from incomplete measurements
EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space
Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
Enhancing Diffusion Models for High-Quality Image Generation
December 18, 2024
PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation
SurgSora: Decoupled RGBD-Flow Diffusion Model for Controllable Surgical Video Generation
IDEQ: an improved diffusion model for the TSP
TAUDiff: Highly efficient kilometer-scale downscaling using generative diffusion models
December 17, 2024
Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance
Rethinking Diffusion-Based Image Generators for Fundus Fluorescein Angiography Synthesis on Limited Data
Towards a Training Free Approach for 3D Scene Editing
Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration