paper-with-me

홈 › Papers

Revisiting Diffusion Model Predictions Through Dimensionality

2026-01-29 · Qing Jin, Chaoyang Wang arxiv

Recent advances in diffusion and flow matching models have highlighted a shift in the preferred prediction target -- moving from noise ($\varepsilon$) and velocity (v) to direct data (x) prediction -- particularly in high-dimensional settings. However, a formal explanation of why the optimal target depends on the specific properties of the data remains elusive. In this work, we provide a theoretical framework based on a generalized prediction formulation that accommodates arbitrary output targets, of which $\varepsilon$-, v-, and x-prediction are special cases. We derive the analytical relationship between data's geometry and the optimal prediction target, offering a rigorous justification for why x-prediction becomes superior when the ambient dimension significantly exceeds the data's intrinsic dimension. Furthermore, while our theory identifies dimensionality as the governing factor for the optimal prediction target, the intrinsic dimension of manifold-bound data is typically intractable to estimate in practice. To bridge this gap, we propose k-Diff, a framework that employs a data-driven approach to learn the optimal prediction parameter k directly from data, bypassing the need for explicit dimension estimation. Extensive experiments in both latent-space and pixel-space image generation demonstrate that k-Diff consistently outperforms fixed-target baselines across varying architectures and data scales, providing a principled and automated approach to enhancing generative performance.

📄 PDF Abstract BibTeX arXiv:2601.21419

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Revisiting Autoregressive Models for Generative Image Classification

2026-03-19 · Ilia Sudakov, Artem Babenko, Dmitry Baranchuk arxiv

Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In t…

Image Classification

Revisiting PCA for time series reduction in temporal dimension

2024-12-27 · Jiaxin Gao, WenBo Hu, Yuntian Chen

Revisiting PCA for Time Series Reduction in Temporal Dimension; Jiaxin Gao, Wenbo Hu, Yuntian Chen; Deep learning has significantly advanced time series analysis (TSA), enabling the extraction of complex patterns for tas…

Computational EfficiencyDimensionality ReductionGPUTime Series+1

Dynamical Regimes of Diffusion Models

2024-02-28 · Giulio Biroli, Tony Bonnaire, Valentin De Bortoli, Marc Mézard

Using statistical physics methods, we study generative diffusion models in the regime where the dimension of space and the number of data are large, and the score function has been trained optimally. Our analysis reveals…

Machine Unlearning for Masked Diffusion Language Models

2026-05-18 · Georu Lee, Seungwon Jeong, Hoki Kim, Jinseong Park 외 arxiv

Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLM…

A New Bayesian Bootstrap for Quantitative Trade and Spatial Models

2025-05-17 · Bas Sanders

Economists use quantitative trade and spatial models to make counterfactual predictions. Because such predictions often inform policy decisions, it is important to communicate the uncertainty surrounding them. Three key …

counterfactual