Related papers: Improvement of Data Analytics Techniques in Reflec…
High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a…
Nanoscale topological polar textures promise new functionalities for ferroelectric memories and logic, yet their three-dimensional structure and mesoscale organization remain experimentally inaccessible. Here we introduce depth-resolved…
Note: The final version of this article was published in Computers and Geosciences, Volume 206, January 2026, 106038. DOI: 10.1016/j.cageo.2025.106038. Readers should refer to the published version for the most up-to-date content.…
Autoencoder (AE) is the key to the success of latent diffusion models for image and video generation, reducing the denoising resolution and improving efficiency. However, the power of AE has long been underexplored in terms of network…
4D-STEM-based orientation and phase mapping has enabled rapid microstructure quantification that can be directly combined with standard TEM- and STEM-based imaging modes. Typically, orientation mapping is coupled with beam precession (i.e.…
Latest diffusion models have shown promising results in category-level 6D object pose estimation by modeling the conditional pose distribution with depth image input. The existing methods, however, suffer from slow convergence during…
In epitaxially strained ferroelectric thin films and superlattices, the ferroelectric transition temperature can lie above the growth temperature. Ferroelectric polarization and domains should then evolve during the growth of a sample, and…
Molecular beam epitaxy is one of the highest quality growth methods, capable of achieving theoretical material property limits and unprecedented device performance. However, such ultimate quality usually comes at the cost of painstaking…
The computational burden of the iterative sampling process remains a major challenge in diffusion-based Low-Light Image Enhancement (LLIE). Current acceleration methods, whether training-based or training-free, often lead to significant…
High-fidelity 3D meshes can be tokenized into one-dimension (1D) sequences and directly modeled using autoregressive approaches for faces and vertices. However, existing methods suffer from insufficient resource utilization, resulting in…
Iron(II) monoxide (FeO) is thermodynamically stable in the halite (w\"ustite) structure only at elevated temperatures in a typically non-stoichiometric, Fe-deficient, Fe$_{1-z}$O form that tends to phase separate and/or transform into…
Halide perovskites are promising semiconductor materials for optoelectronics. One of their unique features is the synthesis, that could be performed by the crystallization from the solution. This method is fast, but practically couldn't be…
The optimization of secondary phase in thermoelectric(TE) materials can {helps in improvisation of material's efficiency}. Being a potential {contender} for lower temperature TE application, bismuth telluride(Bi$_2$Te$_3$) nanoparticles…
While latent diffusion models achieve impressive image editing results, their application to iterative editing of the same image is severely restricted. When trying to apply consecutive edit operations using current models, they accumulate…
Ultrafast-optical-pump -- structural-probe measurements, including ultrafast electron and x-ray scattering, provide direct experimental access to the fundamental timescales of atomic motion, and are thus foundational techniques for studying…
We show how generative machine learning can be used for the rapid computation of strongly dynamical electron diffraction directly from crystal structures, specifically in large-angle convergent-beam electron diffraction (LACBED) patterns.…
Organic-inorganic hybrid perovskites (OIHPs) have recently emerged as groundbreaking semiconductor materials owing to their remarkable properties. Transmission electron microscopy (TEM), as a very powerful characterization tool, has been…
Reflection removal technology plays a crucial role in photography and computer vision applications. However, existing techniques are hindered by the lack of high-quality in-the-wild datasets. In this paper, we propose a novel paradigm for…
The association of scanning transmission electron microscopy (STEM) and the detection of a diffraction pattern at each probe position (so-called 4D-STEM) represents one of the most promising approaches to analyze structural properties of…
Text-to-image diffusion models have achieved remarkable progress in recent years. However, training models for high-resolution image generation remains challenging, particularly when training data and computational resources are limited. In…