diffusion models

Tibetan image enhancement method based on hybrid transform diffusion model

This paper presents a Tibetan low-light image enhancement method based on a hybrid transform diffusion model. We construct TibetanLLIE-400, a dedicated dataset covering scriptures, inscriptions, street signs, and Thangka-related images, to address the scarcity and uneven quality of Tibetan low-light samples. The propos...

SPARTA v2.2.0: graph transport operators and structural null models for spatial omics (code, node tables and results)

SPARTA poses two transport problems on one spatial graph: a source–sink minimum cut for migrating immune cells and a screened diffusion–absorption equation for an IgG-sized molecule. Release v2.2.0 accompanies the manuscript submitted to Interdisciplinary Sciences: Computational Life Sciences and contains the complete...

Neem mediated silver nanoparticles for reactive orange dye adsorption with statistical optimization and artificial neural network modeling

The uncontrolled discharge of synthetic dyes into aquatic systems poses serious environmental and health hazards to humans and animals. Therefore, green, reusable, and effective adsorbents must be developed for sustainable treatment. This study investigated biosynthesized AgNPs as an adsorbent for RO dye removal. To co...

Synthetic Spacecraft Telemetry Dataset with Physics-Constrained Validation

This dataset contains synthetically generated spacecraft telemetry for Low Earth Orbit (LEO) missions using a physics-constrained tabular diffusion framework. The dataset includes spacecraft telemetry parameters generated under different space-weather conditions, including Quiet, Moderate, and Storm scenarios. The tele...

Reaction–diffusion model of avascular pancreatic islet oxygenation and insulin secretion: source code and data

Source code (Python), analysis and figure scripts, and processed simulation-output files for the numerically verified reaction–diffusion model of oxygen transport and insulin secretion in avascular engineered pancreatic islet constructs. All outputs are deterministic; running the provided code reproduces every figure,...

Integrity Auditing and Monte Carlo Limits in Probabilistic InSAR Forecasting: A Willcox Basin Pilot Study

Code and derived results for a development-stage probabilistic forecasting workflow that applies a conditional diffusion model to NASA OPERA DISP-S1 InSAR line-of-sight displacement in the Willcox Basin, Arizona. The workflow implements executable checks of artifact consistency, evaluation eligibility, numerical scope,...

The Diffusion of Cohabitation Among Immigrants in Europe: The Role of the National Cohabitation Context

Abstract Immigrants and their descendants constitute an increasing share of European populations, yet research on how immigrant background shapes the cohabitation experience remains limited. This study investigates how generational status at the individual level and national context at the macro level influence the lik...

Application of a lightweight denoising diffusion model based on few-shot fine-tuning in handwritten digit generation

Diffusion models excel at generative imaging but necessitate extensive datasets and considerable computational power. Few-shot learning with these models frequently results in overfitting and inconsistent generative quality. This study addresses these challenges for resource-constrained diffusion models under severe da...

Methylene Blue Adsorption Using the Metal-Organic Framework of Calcium Alginate (CaA)

Methylene blue (MB) is one of the most commonly used dyes in the printing and textile industries. This research aimed to synthesize MOF CaA (Metal-Organic Framework Calcium Alginate) as an adsorbent for MB dye waste and investigate the effects of contact time and MB concentration on adsorption efficiency. MOF CaA was s...

RLVacDiffSim: Reinforcement learning-driven simulation of vacancy diffusion

Code used to train mean-first-passage-time/time-estimator models and run deep-reinforcement-learning-accelerated atomistic simulations of vacancy diffusion.

TRALF: training-free regional prompt adaptation and layer fusion for transformer-based text-to-image diffusion models

While recent Transformer-based diffusion models have significantly advanced text-to-image (T2I) synthesis, they inherently lack explicit spatial inductive bias. Consequently, generating complex scenes with multiple objects and fine-grained attributes often leads to severe "attribute leakage" and "spatial misalignment....

Wavelet-informed Residual Diffusion Model for medical image super resolution