5 papers
SPICE -- modelling synthetic spectra of stars with non-homogeneous surfaces
M. Jabłońska, T. Różański, L. Casagrande +4
In the era of large time-domain spectro-photometric surveys, surface variations such as starspots, chemical inhomogeneities, pulsations, rotational distortions, and binary interact…
Interpreting deep learning-based stellar mass estimation via causal analysis and mutual information decomposition
Wei Zhang, Qiufan Lin, Yuan-Sen Ting +4
End-to-end deep learning models fed with multi-band galaxy images are powerful data-driven tools used to estimate galaxy physical properties in the absence of spectroscopy. However…
Effective Training Data Synthesis for Improving MLLM Chart Understanding
Yuwei Yang, Zeyu Zhang, Yunzhong Hou +5
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language…
Scaling Laws for Emulation of Stellar Spectra
Tomasz Różański, Yuan-Sen Ting
Neural network-based emulators for the inference of stellar parameters and elemental abundances represent an increasingly popular methodology in modern spectroscopic surveys. Howev…
CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
Qiufan Lin, Hengxin Ruan, Dominique Fouchez +6
Obtaining well-calibrated photometric redshift probability densities for galaxies without a spectroscopic measurement remains a challenge. Deep learning discriminative models, typi…