paper-with-me

홈 › Papers

Latent Abstractions in Generative Diffusion Models

2024-10-04 · Giulio Franzese, Mattia Martini, Giulio Corallo, Paolo Papotti, Pietro Michiardi

In this work we study how diffusion-based generative models produce high-dimensional data, such as an image, by implicitly relying on a manifestation of a low-dimensional set of latent abstractions, that guide the generative process. We present a novel theoretical framework that extends NLF, and that offers a unique perspective on SDE-based generative models. The development of our theory relies on a novel formulation of the joint (state and measurement) dynamics, and an information-theoretic measure of the influence of the system state on the measurement process. According to our theory, diffusion models can be cast as a system of SDE, describing a non-linear filter in which the evolution of unobservable latent abstractions steers the dynamics of an observable measurement process (corresponding to the generative pathways). In addition, we present an empirical study to validate our theory and previous empirical results on the emergence of latent abstractions at different stages of the generative process.

📄 PDF Abstract BibTeX arXiv:2410.03368

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Infinite Gaze Generation for Videos with Autoregressive Diffusion

2026-03-26 · Jenna Kang, Colin Groth, Tong Wu, Finley Torrens 외 arxiv

Predicting human gaze in video is fundamental to advancing scene understanding and multimodal interaction. While traditional saliency maps provide spatial probability distributions and scanpaths offer ordered fixations, …

Scene Understanding

Theoretical guarantees for sampling and inference in generative models with latent diffusions

2019-03-05 · Belinda Tzen, Maxim Raginsky

We introduce and study a class of probabilistic generative models, where the latent object is a finite-dimensional diffusion process on a finite time interval and the observed variable is drawn conditionally on the termi…

Variational Inference

Learning Procedural Abstractions and Evaluating Discrete Latent Temporal Structure

2019-05-01 · ICLR 2019 5 · Karan Goel, Emma Brunskill

Clustering methods and latent variable models are often used as tools for pattern mining and discovery of latent structure in time-series data. In this work, we consider the problem of learning procedural abstractions fr…

ClusteringTime SeriesTime Series Analysis

Latent Diffusion : Multi-Dimension Stable Diffusion Latent Space Explorer

2025-09-26 · Zhihua Zhong, Xuanyang Huang arxiv

Latent space is one of the key concepts in generative AI, offering powerful means for creative exploration through vector manipulation. However, diffusion models like Stable Diffusion lack the intuitive latent vector con…

InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models

2023-06-14 · Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan 외

While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that …

Representation Learning