Related papers: A Probabilistic Autoencoder for Galaxy SED Reconst…

Stack autoencoder (SAE), as a representative deep network, has unique and excellent performance in feature learning, and has received extensive attention from researchers. However, existing deep SAEs focus on original samples without…

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

We present a proof-of-concept analysis of photometric redshifts with Bayesian priors on physical properties of galaxies. This concept is particularly suited for upcoming/on-going large imaging surveys, in which only several broad-band…

We present METAPHOR (Machine-learning Estimation Tool for Accurate PHOtometric Redshifts), a method able to provide a reliable PDF for photometric galaxy redshifts estimated through empirical techniques. METAPHOR is a modular workflow,…

We present a computationally efficient galaxy archetype-based redshift estimation and spectral classification method for the Dark Energy Survey Instrument (DESI) survey. The DESI survey currently relies on a redshift fitter and spectral…

We present SHEEP, a new machine learning approach to the classic problem of astronomical source classification, which combines the outputs from the XGBoost, LightGBM, and CatBoost learning algorithms to create stronger classifiers. A novel…

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…

We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and…

As a logical next step in improving the radio-to-submm spectral index as a redshift indicator (Carilli & Yun 1999), we have investigated a technique of using the entire radio-to-FIR spectral energy distribution (SED) for deriving…

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…

Neural Networks play a growing role in many science disciplines, including physics. Variational Autoencoders (VAEs) are neural networks that are able to represent the essential information of a high dimensional data set in a low dimensional…

Efficiently solving the Fokker-Planck equation (FPE) is crucial for understanding the probabilistic evolution of stochastic particles in dynamical systems, however, analytical solutions or density functions are only attainable in specific…

This paper explores Masked Autoencoders (MAE) with Gaussian Splatting. While reconstructive self-supervised learning frameworks such as MAE learns good semantic abstractions, it is not trained for explicit spatial awareness. Our approach,…

This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an…

In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior…

Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features. Despite recent excitement about their potential, research…

Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025) have highlighted instability across different initialization…

We present piXedfit, pixelized spectral energy distribution (SED) fitting, a Python package that provides tools for analyzing spatially resolved properties of galaxies using multiband imaging data alone or in combination with integral field…

Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their…

High-throughput phenotypic screens generate vast microscopy image datasets that push the limits of generative models due to their large dimensionality. Despite the growing popularity of general-purpose models trained on natural images for…