![[2606.03820] A Quantitative Approximation Framework for Flow Distillation in Diffusion Models](/static/img/curated/desks/afbytes-tech.png)
[2606.03820] A Quantitative Approximation Framework for Flow Distillation in Diffusion Models
Abstract page for arXiv paper 2606.03820: A Quantitative Approximation Framework for Flow Distillation in Diffusion Models
America Forever Bytes
Diffusion Models · AFBytes
Technology
Diffusion Models
Recent coverage
[2606.00366] GLENS: Global Search via Learning from Solver Iterates with Diffusion Models
Abstract page for arXiv paper 2606.00366: GLENS: Global Search via Learning from Solver Iterates with Diffusion Models
[2606.02607] Geometry-Aware Tabular Diffusion
Abstract page for arXiv paper 2606.02607: Geometry-Aware Tabular Diffusion
[2606.00567] Activation Concentration: Characterizing Column-Level Output Sparsity Across Diffusion Model Architectures
Abstract page for arXiv paper 2606.00567: Activation Concentration: Characterizing Column-Level Output Sparsity Across Diffusion Model Architectures
[2606.01645] Self-Regulating Annealing in Heavy-Tailed Diffusion Models
Abstract page for arXiv paper 2606.01645: Self-Regulating Annealing in Heavy-Tailed Diffusion Models
[2606.02237] Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
Abstract page for arXiv paper 2606.02237: Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
[2606.01461] Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models
Abstract page for arXiv paper 2606.01461: Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Model...
[2605.30614] Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
Abstract page for arXiv paper 2605.30614: Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
[2605.30747] Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models
Abstract page for arXiv paper 2605.30747: Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models
[2605.31564] What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation
Abstract page for arXiv paper 2605.31564: What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation
[2605.30153] Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
Abstract page for arXiv paper 2605.30153: Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
[2605.29569] LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
Abstract page for arXiv paper 2605.29569: LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
[2605.16415] Diffusion Models, Denoiser Architecture and Creativity
Abstract page for arXiv paper 2605.16415: Diffusion Models, Denoiser Architecture and Creativity
[2605.27975] Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
Abstract page for arXiv paper 2605.27975: Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
[2605.27919] Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
Abstract page for arXiv paper 2605.27919: Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
[2605.28711] Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
Abstract page for arXiv paper 2605.28711: Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
[2605.28036] Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
Abstract page for arXiv paper 2605.28036: Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
[2605.28067] BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models
Abstract page for arXiv paper 2605.28067: BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models