I am a last-year Ph.D. student at the University of Basel. I was a researcher at University College London (UCL) for 9 months in 2023. I work with Prof. Ivan Dokmanić and Prof. Jason McEwen. My research lies at the intersection of deep learning and computational imaging. I am interested in building physics-informed neural networks for solving scientific inverse problems.

           



News

  • July 2024: I have been invited by the Signal Processing Society (SPS) to present a webinar on deep generative models for Bayesian imaging.
  • May 2024: I give a talk on physics-informed neural networks for cosmological inverse problems at the Cosmo 21 Conference in Chania, Greece.
  • Jan 2024: Our recent preprint is now available on ArXiv.
  • Nov 2023: Our paper “Conditional Injective Flows for Bayesian Imaging” is among the top 25 most downloaded papers in IEEE Transactions on Computational Imaging (TCI) from Sept. 2022 - Sept. 2023.
  • Aug 2023: Our paper “Deep Injective Prior for Inverse Scattering” has been accepted by IEEE Transactions on Antennas and Propagation.
  • July 2023: I am awarded a grant by the Promotion of Young Talent at the University of Basel to spend 9 months as a visiting scholar at University College London (UCL), focused on leveraging deep generative models for astrophysics in Prof. Jason McEwen’s group.
  • Feb 2023: Our paper “Conditional Injective Flows for Bayesian Imaging” has been accepted by IEEE Transactions on Computational Imaging.
  • Jan 2023: Our paper “FunkNN: Neural Interpolation for Functional Generation” has been accepted by ICLR 2023.
  • Dec 2022: Our paper has been accepted by European Conference on Antennas and Propagation (EUCAP 2023).
  • Jun 2021: Our paper has been accepted by the Conference on Uncertainty in Artificial Intelligence (UAI 2021).
  • April 2020: I started my Ph.D. at the SADA group, University of Basel.



Publications




GLIMPSE: Generalized Local Imaging with MLPs
AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu and Ivan Dokmanić
Preprint 2024

      





FunkNN: Neural Interpolation for Functional Generation
AmirEhsan Khorashadizadeh, Anadi Chaman, Valentin Debarnot and Ivan Dokmanić
ICLR 2023

       


Deep Injective Prior for Inverse Scattering
AmirEhsan Khorashadizadeh, Vahid Khorashadizadeh, Sepehr Eskandari, Guy A.E. Vandenbosch and Ivan Dokmanić
IEEE Transactions on Antennas and Propagation 2023

       


Conditional Injective Flows for Bayesian Imaging
AmirEhsan Khorashadizadeh, Konik Kothari, Leonardo Salsi, Ali Aghababaei Harandi, Maarten de Hoop and Ivan Dokmanić
IEEE Transactions on Computational Imaging 2023

       


Deep Variational Inverse Scattering
AmirEhsan Khorashadizadeh, Ali Aghababaei, Tin Vlavsić, Hieu Nguyen and Ivan Dokmanić
European Conference on Antennas and Propagation (EuCAP) 2023

       




Implicit Neural Representation for Mesh-Free Inverse Obstacle Scattering
Tin Vlašić, Hieu Nguyen, AmirEhsan Khorashadizadeh and Ivan Dokmanić
Asilomar Conference on Signals, Systems, and Computers 2022





Trumpets: Injective flows for inference and inverse problems
Konik Kothari, AmirEhsan Khorashadizadeh, Maarten de Hoop and Ivan Dokmanić
UAI 2021