Tootfinder

Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability
Rog\'erio Almeida Gouv\^ea, Pierre-Paul De Breuck, Tatiane Pretto, Gian-Marco Rignanese, Marcos Jos\'e Leite dos Santos
https://arxiv.org/abs/2509.03547

Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability
This study introduces MatterVial, an innovative hybrid framework for feature-based machine learning in materials science. MatterVial expands the feature space by integrating latent representations from a diverse suite of pretrained graph neural network (GNN) models including: structure-based (MEGNet), composition-based (ROOST), and equivariant (ORB) graph networks, with computationally efficient, GNN-approximated descriptors and novel features from symbolic regression. Our approach combines the…

ConfLogger: Enhance Systems' Configuration Diagnosability through Configuration Logging
Shiwen Shan, Yintong Huo, Yuxin Su, Zhining Wang, Dan Li, Zibin Zheng
https://arxiv.org/abs/2508.20977

ConfLogger: Enhance Systems' Configuration Diagnosability through Configuration Logging
Modern configurable systems offer customization via intricate configuration spaces, yet such flexibility introduces pervasive configuration-related issues such as misconfigurations and latent softwarebugs. Existing diagnosability supports focus on post-failure analysis of software behavior to identify configuration issues, but none of these approaches look into whether the software clue sufficient failure information for diagnosis. To fill in the blank, we propose the idea of configuration logg…

Latent space projections and atlases: A cautionary tale in deep neuroimaging using autoencoders
J. M. Gorriz, F. Segovia, C. Jimenez, J. E. Arco, F. J. Martinez, J Ramirez, S. Abulikemu, J. Suckling
https://arxiv.org/abs/2509.03675

Latent space projections and atlases: A cautionary tale in deep neuroimaging using autoencoders
This study introduces a deep learning pipeline for the unsupervised analysis of 3D brain MRI using a simple convolutional autoencoder architecture. Trained on segmented gray matter images from the ADNI dataset, the model learns compact latent representations that preserve neuroanatomical structure and reflect clinical variability across cognitive states. We apply dimensionality reduction techniques (PCA, tSNE, PLS, UMAP) to visualize and interpret the latent space, correlating it with anatomica…

Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis
Trinh Ngoc Huynh, Nguyen Duc Kien, Nguyen Hai Anh, Dinh Tran Hiep, Manuela Vaneckova, Tomas Uher, Jeroen Van Schependom, Stijn Denissen, Tran Quoc Long, Nguyen Linh Trung, Guy Nagels
https://arxiv.org/abs/2510.00051

Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis
We present InfoVAE-Med3D, a latent-representation learning approach for 3D brain MRI that targets interpretable biomarkers of cognitive decline. Standard statistical models and shallow machine learning often lack power, while most deep learning methods behave as black boxes. Our method extends InfoVAE to explicitly maximize mutual information between images and latent variables, producing compact, structured embeddings that retain clinically meaningful content. We evaluate on two cohorts: a lar…

A Data-Adaptive Factor Model Using Composite Quantile Approach
Seeun Park, Hee-Seok Oh
https://arxiv.org/abs/2510.00558 https://arxiv.org/pdf/2510.00558

A Data-Adaptive Factor Model Using Composite Quantile Approach
This paper proposes a data-adaptive factor model (DAFM), a novel framework for extracting common factors that explain the structures of high-dimensional data. DAFM adopts a composite quantile strategy to adaptively capture the full distributional structure of the data, thereby enhancing estimation accuracy and revealing latent patterns that are invisible to conventional factor models. In this paper, we develop a practical algorithm for estimating DAFM by minimizing an objective function based o…

Autoencoder-based non-intrusive model order reduction in continuum mechanics
Jannick Kehls, Ellen Kuhl, Tim Brepols, Kevin Linka, Hagen Holthusen
https://arxiv.org/abs/2509.02237

Autoencoder-based non-intrusive model order reduction in continuum mechanics
We propose a non-intrusive, Autoencoder-based framework for reduced-order modeling in continuum mechanics. Our method integrates three stages: (i) an unsupervised Autoencoder compresses high-dimensional finite element solutions into a compact latent space, (ii) a supervised regression network maps problem parameters to latent codes, and (iii) an end-to-end surrogate reconstructs full-field solutions directly from input parameters. To overcome limitations of existing approaches, we propose two…

Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
Gautier Evennou, Vivien Chappelier, Ewa Kijak
https://arxiv.org/abs/2510.00799 https://

Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
Most image watermarking systems focus on robustness, capacity, and imperceptibility while treating the embedded payload as meaningless bits. This bit-centric view imposes a hard ceiling on capacity and prevents watermarks from carrying useful information. We propose LatentSeal, which reframes watermarking as semantic communication: a lightweight text autoencoder maps full-sentence messages into a compact 256-dimensional unit-norm latent vector, which is robustly embedded by a finetuned watermar…

Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models
Valentin Delchevalerie, Nicolas Roy, Arnaud Bougaham, Alexandre Mayer, Beno\^it Fr\'enay, Micha\"el Lobet
https://arxiv.org/abs/2510.01749

Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models
Photonic crystals enable fine control over light propagation at the nanoscale, and thus play a central role in the development of photonic and quantum technologies. Photonic band diagrams (BDs) are a key tool to investigate light propagation into such inhomogeneous structured materials. However, computing BDs requires solving Maxwell's equations across many configurations, making it numerically expensive, especially when embedded in optimization loops for inverse design techniques, for example.…

Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Shilin Lu, Zhuming Lian, Zihan Zhou, Shaocong Zhang, Chen Zhao, Adams Wai-Kin Kong
https://arxiv.org/abs/2509.21278

Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections) and diverse, high-resolution inputs. Modern text-to-image diffusion models (e.g., SD3.5, FLUX) already encode essential physical and resolution priors, yet lack a framework to unleash them without resorting to latent inversion, which often locks object poses into contextually inappropriate orientations, or brittle at…

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
Junlin Han, Shengbang Tong, David Fan, Yufan Ren, Koustuv Sinha, Philip Torr, Filippos Kokkinos
https://arxiv.org/abs/2509.26625

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
Large Language Models (LLMs), despite being trained on text alone, surprisingly develop rich visual priors. These priors allow latent visual capabilities to be unlocked for vision tasks with a relatively small amount of multimodal data, and in some cases, to perform visual tasks without ever having seen an image. Through systematic analysis, we reveal that visual priors-the implicit, emergent knowledge about the visual world acquired during language pre-training-are composed of separable percep…