Skip to content

Category

diffusion models

2,136 papers

#diffusion models Open access Sep 2026

When global training meets local practice: narratives of South African STEM teacher educators navigating OER and OEP training

This study examines how teacher educators interpret and recontextualise pedagogical knowledge encountered in international educational technology training initiatives. Drawing on narrative inquiry and autoethnographic reflection, the article presents the experiences of two South African STEM teacher educators who parti...

Liztie Prinsloo, Zaheera Jina Asvat · 0 citations
#diffusion models Open access Sep 2026

A Plaintext-coupled Puzzle-based Image Encryption Scheme Using Dynamic Permutation and Nonlinear Diffusion

Chaos-based image ciphers built on a permutation-diffusion structure are effective, but most rely on regular block shuffles or single-pass global diffusion, and few report the cryptographic properties of their internal building blocks.This paper proposes a puzzle-based image encryption scheme in which square image piec...

Devaraj F V, Jalesh Kumar · 0 citations
#diffusion models Open access Sep 2026

jenswag/eve: Name update

Hybrid model for predicting composition-dependent mutual diffusion coefficients in liquid mixtures

Jens Wagner · 0 citations
#diffusion models Open access Sep 2026

Gradient porosity anodes for enhancing the electrochemical and thermomechanical performance of methanol-fueled SOFC

During practical operation of methanol-fueled solid oxide fuel cell (SOFC), the endothermic reforming induces large temperature gradients and high first principal stress, accelerating cell degradation. To improve the thermomechanical performance of methanol-fueled SOFC, gradient-porosity anodes are proposed in this wor...

Wenbin Xie, Haoteng Yuan, Yinghui Sun et al. · 0 citations
#diffusion models Dataset Open access Sep 2026

Pretrained diffusion checkpoints for GSS and RSS material datasets

Description This record provides the pretrained CSP diffusion model used by GSS (Generative Structure Search), a framework that combines diffusion generative models with energy-based guidance from machine-learning force fields to search for stable crystal structures. The paper's main experiments target periodic crystal...

Yifang Qin · 0 citations
#diffusion models Open access Sep 2026

Relational Model of Informational Geometry (RMIG): Emergent gravity, Standard Model, and cosmological constant from the entanglement budget on the 18/27 qubit fractal

We present the Relational Model of Informational Geometry (RMIG) — a theory proposing a common mechanism for the emergence of spacetime, gravity, gauge interactions, and the cosmological constant from the finite quantum entanglement budget on a qubit network embedded on the self-similar 18/27 fractal. Of the 27 neighbo...

SŁAWOMIR RAMIAN · 0 citations
#diffusion models Open access Sep 2026

Deterministic Electrochemical Battery State Estimation via Volume-Weighted Lithium Mass Hyperplane Projections: Achieving Zero-Drift SoC and Hard Real-Time BMS on Microcontrollers

Precise on-board estimation of State of Charge (SoC) and State of Health (SoH) in lithium-ion battery management systems (BMS) remains a critical bottleneck in electric vehicle range predictability, fast-charging safety, and pack longevity. Conventional BMS firmware is polarized between two inadequate paradigms: empiri...

A. Emre Cetin · 0 citations
#diffusion models Book Sep 2026

Fostering Sustainable Economic Transformation in BRICS Through Innovation and Knowledge Exchange

Abstract This chapter examines how innovation and knowledge exchange can act as key enablers of sustainable economic transformation within BRICS economies – Brazil, Russia, India, China and South Africa. Set against the backdrop of climate change, resource constraints and socio-economic inequalities, this chapter argue...

Yogesh Sharma, Ankit Suri · 0 citations
#generative ai Dataset Open access Sep 2026

Calibrated Residual Tube Projection During Conditional Diffusion Sampling for Thermal Time Series — Code and Experimental Evidence

Code and experimental evidence supporting Calibrated Residual Tube Projection During Conditional Diffusion Sampling for Thermal Time Series, by Hyojin Park and Jinhong Yang (corresponding author). The release contains the selected B6 checkpoint, original method implementations, exact simulator and score settings, froze...

Hyojin Park, Jinhong Yang · 0 citations
#diffusion models Open access Sep 2026

Relational Model of Informational Geometry (RMIG): Emergent gravity, Standard Model, and cosmological constant from the entanglement budget on the 18/27 qubit fractal

We present the Relational Model of Informational Geometry (RMIG) — a theory proposing a common mechanism for the emergence of spacetime, gravity, gauge interactions, and the cosmological constant from the finite quantum entanglement budget on a qubit network embedded on the self-similar 18/27 fractal. Of the 27 neighbo...

SŁAWOMIR RAMIAN · 0 citations
#diffusion models Open access Sep 2026

Normalize, Clean, Resample, and Train (NCRT): An End-to-End Pipeline Study for Solar Energetic Particle Forecasting

Abstract Solar energetic particle (SEP) events are rare, high-impact space weather phenomena that pose serious radiation hazards to astronauts and polar-route aircraft crews, damage satellite electronics, and disrupt satellite communications and navigation systems. Forecasting SEPs allows preventive measures to be take...

MohammadReza EskandariNasab, Garrett Woodhouse, Shah Muhammad Hamdi et al. · 0 citations
#diffusion models Open access Sep 2026

DriftJax: A Differentiable 1-D Drift-Diffusion Solar-Cell Simulator in JAX

DriftJax is a one-dimensional, end-to-end differentiable photovoltaic cell simulator based on the drift-diffusion model and the Beer-Lambert law for optical absorption, programmed in Python using JAX. Gradients of the power conversion efficiency (and any scalar figure of merit) with respect to device design parameters...

Mohammed Benaissa, Mohamed MaoudJ, Abd Elouahab Noua · 0 citations

From tech blogs

See all →
Microsoft Research Blog Oct 12, 2026

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.