Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders

• URL: http://arxiv.org/abs/2606.14999v1
• Date: Fri, 12 Jun 2026 22:37:27 GMT
• Title: Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders
• Abstract summary: We train a domain-specific attention-based Convolutional Variational Autoencoder on 1.5 million X-ray scattering images.<n>When deployed without retraining, the model organizes time-resolved film formation experiments into interpretable latent structures.
• Score: 23.47770035620871
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific user facilities generate X-ray scattering data faster than traditional workflows can process them. We address this challenge across two settings, offline dataset exploration and live on-the-fly analysis. We train a domain-specific attention-based Convolutional Variational Autoencoder (C-VAE) on 1.5 million X-ray scattering images to learn low-dimensional representations capturing structural variation across diverse experimental conditions. The learned latent space reveals well-organized clusters and smooth trajectories reflecting experimental progression. It further supports controlled synthetic scattering image generation across diverse structural states. When deployed without retraining, the model organizes time-resolved film formation experiments at two synchrotron facilities into interpretable latent structures. Benchmarking against DINOv3 (ViT-7B), a general-purpose vision foundation model, demonstrates that domain-specific training yields more interpretable latent organization for scattering data. Both workflows are integrated within Latent Space Explorer, a component of the MLExchange platform, supporting interactive structural exploration across archived datasets and live experiments.

Related papers

• FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales [65.4821703903285]
  FLORO is a multimodal foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus.<n> FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data.<n>We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks.
  arXiv  Detail & Related papers  (2026-05-27T08:55:54Z)
• OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation [100.36917520403227]
  We present a unified text-conditioned diffusion framework that generates LiDAR scans in a shared range-image representation across eight representative domains.<n>In the absence of a public consolidated benchmark, we construct an 8-domain dataset by combining real-world scans with physically based weather simulation and systematic beam reduction.
  arXiv  Detail & Related papers  (2026-05-13T17:42:20Z)
• Context-Aware Multimodal Representation Learning for Spatio-Temporally Explicit Environmental Modelling [3.3984815208531014]
  We propose a representation learning framework that integrates different modalities into unified space at high-temporal resolution.<n>Our approach produces a latent space at native 10 m resolution and the temporal frequency of cloud-free Sentinel-2 data.<n>This enables the model to capture complementary remote sensing data and to preserve coherence across space and time.
  arXiv  Detail & Related papers  (2025-11-12T15:34:17Z)
• Packet-Level DDoS Data Augmentation Using Dual-Stream Temporal-Field Diffusion [2.8498570090658726]
  In response to Distributed Denial of Service (DDoS) attacks, recent research efforts increasingly rely on Machine Learning (ML)-based solutions.<n>Current synthetic trace generation methods struggle to capture the complex temporal patterns and spatial distributions exhibited in emerging DDoS attacks.<n>We propose Dual-Stream Temporal-Field Diffusion (DSTF-Diffusion), a multi-view, multi-stream network traffic generative model based on diffusion models.
  arXiv  Detail & Related papers  (2025-07-27T03:40:56Z)
• XxaCT-NN: Structure Agnostic Multimodal Learning for Materials Science [0.27185251060695437]
  We propose a scalable framework that learns directly from elemental composition and X-ray diffraction (XRD)<n>Our architecture integrates modality-specific encoders with a cross-attention fusion module and is trained on the 5-million-sample Alexandria dataset.<n>Our results establish a path toward structure-free, experimentally grounded foundation models for materials science.
  arXiv  Detail & Related papers  (2025-06-27T21:45:56Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving [88.85002707211777]
  LargeAD is a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets.<n>Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds.<n>This alignment facilitates cross-modal representation learning, enhancing the semantic consistency between 2D and 3D data.
  arXiv  Detail & Related papers  (2025-01-07T18:59:59Z)
• Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World [83.36195426897768]
  We propose VRVO, a novel framework for retrieving the absolute scale from virtual data. We first train a scale-aware disparity network using both monocular real images and stereo virtual data. The resulting scale-consistent disparities are then integrated with a direct VO system.
  arXiv  Detail & Related papers  (2022-03-11T01:51:54Z)
• Tracking perovskite crystallization via deep learning-based feature detection on 2D X-ray scattering data [137.47124933818066]
  We propose an automated pipeline for the analysis of X-ray diffraction images based on the Faster R-CNN deep learning architecture. We demonstrate our method on real-time tracking of organic-inorganic perovskite structure crystallization and test it on two applications.
  arXiv  Detail & Related papers  (2022-02-22T15:39:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.