A CNN with attention and shared latent space recovers SFHs and metallicities from spectro-photometric data with ~0.12 dex age and ~0.03 dex metallicity dispersion while running thousands of times faster than full spectral fitting.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
SHEAP introduces a GPU-accelerated JAX framework for AGN spectral decomposition that achieves ~100x speedup over pPXF with 85-100% parameter agreement within 0.3 dex on four test samples.
UniRTL unifies RTL code and CDFG through mutual masked modeling and hierarchical training with a graph-aware tokenizer, outperforming prior single-modality methods on performance prediction and code retrieval.
Constructs a computable approximating prediction region containing the full-conformal one for multi-task kernel regression in vector-valued RKHS, with theoretical volume bound for known covariance and empirical improvement over split-conformal.
citing papers explorer
-
Determining star formation histories and age-metallicity relations with convolutional neural networks
A CNN with attention and shared latent space recovers SFHs and metallicities from spectro-photometric data with ~0.12 dex age and ~0.03 dex metallicity dispersion while running thousands of times faster than full spectral fitting.
-
Spectral Handling and Estimation of AGN Parameters (SHEAP), The first AGN fitting GPU-based code
SHEAP introduces a GPU-accelerated JAX framework for AGN spectral decomposition that achieves ~100x speedup over pPXF with 85-100% parameter agreement within 0.3 dex on four test samples.
-
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
UniRTL unifies RTL code and CDFG through mutual masked modeling and hierarchical training with a graph-aware tokenizer, outperforming prior single-modality methods on performance prediction and code retrieval.
-
Approximate full-conformal multi-task regression with reproducing kernels
Constructs a computable approximating prediction region containing the full-conformal one for multi-task kernel regression in vector-valued RKHS, with theoretical volume bound for known covariance and empirical improvement over split-conformal.