相关论文: SpectroTranslator: a deep-neural network algorithm…

Large-scale spectroscopic surveys have collectively observed millions of stars across the Milky Way, but each derives stellar labels using independent pipelines with distinct modelling assumptions, introducing systematic offsets that…

Spectroscopy is a powerful analytical technique for characterizing matter across physical and biological realms1-5. However, its fundamental principle necessitates specialized instrumentation per physical phenomena probed, limiting broad…

Spectroscopic surveys require fast and efficient analysis methods to maximize their scientific impact. Here we apply a deep neural network architecture to analyze both SDSS-III APOGEE DR13 and synthetic stellar spectra. When our…

Deep learning with artificial neural networks is increasingly gaining attention, because of its potential for data-driven astronomy. However, this methodology usually does not provide uncertainties and does not deal with incompleteness and…

This paper proposes a parameter collaborative optimization algorithm for large language models, enhanced with graph spectral analysis. The goal is to improve both fine-tuning efficiency and structural awareness during training. In the…

We present a machine learning method to assign stellar parameters (temperature, surface gravity, metallicity) to the photometric data of large photometric surveys such as SDSS and SKYMAPPER. The method makes use of our previous effort in…

In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous…

Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-point maps, a Transformer acts as a measure-to-measure map…

Using machine learning, we explore the utility of various deep neural networks (NN) when applied to high harmonic generation (HHG) scenarios. First, we train the NNs to predict the time-dependent dipole and spectra of HHG emission from…

This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some equivalence of the graph convolution process regardless it is…

An applied problem facing all areas of data science is harmonizing data sources. Joining data from multiple origins with unmapped and only partially overlapping features is a prerequisite to developing and testing robust, generalizable…

With the large amounts of spectroscopic data available today and the very large surveys to come (e.g. Gaia), the need for automatic data analysis software is unquestionable. We thus developed an automatic spectra analysis program for the…

Large language models have emerged as transformative tools in molecular science, demonstrating remarkable potential in molecular property prediction and de novo molecular design. However, their application to spectroscopy remains notably…

Generalized from image and language translation, graph translation aims to generate a graph in the target domain by conditioning an input graph in the source domain. This promising topic has attracted fast-increasing attention recently.…

Motivated by the limitations of current spectral analysis methods-such as reliance on single-modality data, limited generalizability, and poor interpretability-we propose a novel multi-modal spectral analysis framework that integrates prior…

Deep learning holds immense promise for spectroscopy, yet research and evaluation in this emerging field often lack standardized formulations. To address this issue, we introduce SpectrumLab, a pioneering unified platform designed to…

In this paper, we investigate the use of transformers for Neural Machine Translation of text-to-GLOSS for Deaf and Hard-of-Hearing communication. Due to the scarcity of available data and limited resources for text-to-GLOSS translation, we…

We propose deep parameter interpolation (DPI), a general-purpose method for transforming an existing deep neural network architecture into one that accepts an additional scalar input. Recent deep generative models, including diffusion…

Hypergraphs play a pivotal role in the modelling of data featuring higher-order relations involving more than two entities. Hypergraph neural networks emerge as a powerful tool for processing hypergraph-structured data, delivering…

Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared…