arXiv Machine Learning
From Seeds to Semantics: Measuring Semantic Accessibility in Deterministic Diffusion Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 7
How Do Diffusion Classifiers Decide? A Bias-Centric Evaluation
arXiv:2607. 03831v1 Announce Type: cross Abstract: Diffusion models have recently been repurposed for zero-shot classification, giving rise to diffusion classifiers that identify the best-matching text prompt by minimizing the noise-prediction error.
arXiv Computer Vision
Sep 7
PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization
PAPT++ is a risk‑aware adversarial generation‑training framework designed to improve single domain generalization. It learns diverse semantic reference images per class and uses them as denoising targets in classifier‑guided diffusion synthesis, thereby generating challenging yet semantically consistent samples. These samples are iteratively combined with source data to update the classifier, progressively exposing it to difficult variations and enhancing generalization performance on standard benchmarks.
arXiv AI
Aug 17
Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation
arXiv:2608. 14172v1 Announce Type: cross Abstract: Text-to-image diffusion models have two major drawbacks that severely limit their practical utility: (1) standard models lack an intrinsic mechanism for continuous, concept-specific guidance (e.
arXiv AI
3d ago
ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images
ReGain is a training‑free correction that improves subject fidelity in text‑to‑image diffusion models personalized with synthetic images. The authors show that fine‑tuning on synthetic images degrades fidelity due to inflated classifier‑free guidance, especially at high frequencies. ReGain measures this inflation per frequency band and scales it down during sampling, closing 51‑64% of the fidelity gap on Stable Diffusion v1.5 and improving performance on SDXL and SD 3.5 while preserving text alignment.
arXiv Computer Vision
Aug 26
AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer
arXiv:2608.23864v1 Announce Type: new Abstract: Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be or...
arXiv AI
Jul 23
On the Separability of Information in Diffusion Models
arXiv:2509. 23937v5 Announce Type: replace-cross Abstract: Diffusion models transform noise into data by injecting information that was captured in their neural network during the training phase.