Precision galaxy morphology recovery for petascale astronomy: A Physics-informed dual-domain transformer approach

LFCD-Net: physics-inspired 3D reconstruction architecture for miniature light-field microscopy

A physics inspired light-field characteristic driven 3D reconstruction network integrating three core innovations: spatial-angular feature blocks for aliasing suppression, multi-scale feature blocks for structural fidelity, and a physics-inspired adaptive weighting loss to ensure high-quality reconstruction of sparse b...

Physics-informed ensemble learning for exoplanet transit detection: Combining box least squares, attention-based CNNs, and gradient boosting

Flow-variational auto-encoder for the data augmentation of the Horizon-AGN dual-AGN dataset

A variational auto-encoder (VAE) with a normalising flow is constructed, developing a specific training loss function for the VAE in both the direct and Fourier spaces, which has enabled the construction of the small-scale and thin features associated with the gravitational interaction between merging galaxies like tid...

Decoupling candidate dual AGN from chance superpositions in the GOTHIC survey via a deep-learning framework

Dual active galactic nuclei (DAGN) mark a critical phase in the evolution of merging galaxies and the pairing of supermassive black holes, yet they remain difficult to identify in large imaging surveys because of projection effects and limited spatial resolution. Compact foreground stars and unresolved substructure can...

Master 2 internship – Physics-informed deep learning for exoplanet detection at high-contrast from multi-variate data

This project will build on recent advances in modeling the nuisance component that corrupts high-contrast total intensity observations, and focus on improving exoplanet detection and characterization using data of cutting-edge ground-based and space-based telescopes.

Blind Image Deblurring in Dynamic Scenes Using Physics-Informed Neural Networks

PI-NAFDeblur is presented, a physics-informed neural network that utilizes a coupling of a lightweight NAFNet restoration backbone and a differentiable reblur operator that enforces forward-model consistency during training to demonstrate that physics-informed regularization can help improve cross-dataset robustness un...