Related papers: An Online Dynamic Amplitude-Correcting Gradient Es…
We propose X-NeRF, a novel method to learn a Cross-Spectral scene representation given images captured from cameras with different light spectrum sensitivity, based on the Neural Radiance Fields formulation. X-NeRF optimizes camera poses…
Random fiber laser (RFL) based on random distributed feedback and Raman gain has earned much attention in recent years. In this presentation, we demonstrate a powerful linearly polarized RFL with spectral adjustment, in which the central…
Offline reinforcement learning (RL) enables policy learning from static data but often suffers from poor coverage of the state-action space and distributional shift problems. This problem can be addressed by allowing limited online…
Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks. Non-learning based methods utilize different handcrafted priors such as the separable sparse gradients caused…
One of the options for increasing longitudinal coherency of X-ray free electron lasers (XFELs) is their seeding with microbunched electron beam. Several schemes leading to significant amplitude of the beam bunching at X-ray wavelengths were…
eXplanation Based Learning (XBL) is an interactive learning approach that provides a transparent method of training deep learning models by interacting with their explanations. XBL augments loss functions to penalize a model based on…
Serial electron diffraction (SerialED) is an emerging technique, which applies the snapshot data-collection mode of serial X-ray crystallography to three-dimensional electron diffraction (3D ED), forgoing the conventional rotation method.…
Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to…
XUV and X-ray Free Electron Lasers (FELs) produce short wavelength pulses with high intensity, ultrashort duration, well-defined polarization and transverse coherence, and have been utilised for many experiments previously possible at long…
PAL-XFEL, a 4th generation light source, is currently being installed and will be completed by December of 2015 so that users can be supported beginning in 2016. PAL-XFEL equipment should continuously maintain the bunch-to-bunch beam…
Neural radiance fields enable novel-view synthesis and scene reconstruction with photorealistic quality from a few images, but require known and accurate camera poses. Conventional pose estimation algorithms fail on smooth or self-similar…
Representation learning (RL) methods learn objects' latent embeddings where information is preserved by distances. Since distances are invariant to certain linear transformations, one may obtain different embeddings while preserving the…
Resonant inelastic x-ray scattering (RIXS) is a widely used spectroscopic technique, providing access to the electronic structure and dynamics of atoms, molecules, and solids. However, RIXS requires a narrow bandwidth x-ray probe to achieve…
X-ray free-electron lasers (XFELs) with megahertz repetition rate can provide novel insights into structural dynamics of biological macromolecule solutions. However, very high dose rates can lead to beam-induced dynamics and structural…
The conjugation of multiple spatial light modulators (SLMs) enables the construction of optical diffractive neural networks (DNNs). To accelerate training, which is limited by the low refresh rate of SLMs, spatial multiplexing of the input…
One of the main challenges in reinforcement learning (RL) is that the agent has to make decisions that would influence the future performance without having complete knowledge of the environment. Dynamically adjusting the level of epistemic…
Diffractive/refractive optics, such as Phase Fresnel Lenses (PFL's), offer the potential to achieve excellent imaging performance in the x-ray and gamma-ray photon regimes. In principle, the angular resolution obtained with these devices…
Single particle diffraction imaging experiments at free-electron lasers (FEL) have a great potential for structure determination of reproducible biological specimens that can not be crystallized. One of the challenges in processing the data…
In a scanning transmission electron microscope (STEM), producing a high-resolution image generally requires an electron beam focused to the smallest point possible. However, the magnetic lenses used to focus the beam are unavoidably…
The framework of deep reinforcement learning (DRL) provides a powerful and widely applicable mathematical formalization for sequential decision-making. This paper present a novel DRL framework, termed \emph{$f$-Divergence Reinforcement…