Related papers: Towards Foundation Models for Experimental Readout…
In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…
Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work,…
We discuss here new, enabling technologies for future photon-based neutrino detectors. These technologies touch nearly every aspect of such detectors: new scintillating materials, new methods of loading isotopes, new photon sensors and…
The next generation of imaging atmospheric Cherenkov telescopes will be composed of hundreds of telescopes working together to attempt to unveil some fundamental physics of the high-energy Universe. Along with the scientific data, a large…
Imaging Cherenkov detectors are largely used in modern nuclear and particle physics experiments where cutting-edge solutions are needed to face always more growing computing demands. This is a fertile ground for AI-based approaches and at…
Accurate characterization of carbon nanotube morphologies in electron microscopy images is vital for exposure assessment and toxicological studies, yet current workflows rely on slow, subjective manual segmentation. This work presents a…
Precision polarimetry is essential for future e+ e- colliders and requires Compton polarimeters designed for negligible statistical uncertainties. In this paper, we discuss the design and construction of a quartz Cherenkov detector for such…
A prototype detector is being developed which combines the functions of a Time Projection Chamber for charged particle tracking and a Cherenkov detector for particle identification. The TPC consists of a 10x10x10 cm3 drift volume where the…
Cryo-electron microscopy can now routinely deliver atomic resolution structures for a variety of biological systems. The relevance and value of these structures is directly related to their ability to help rationalize experimental…
The properties of excited nuclear matter and the quest for a phase transition which is expected to exist in this system are the subject of intensive investigations. High energy nuclear collisions between finite nuclei which lead to matter…
We present the reduced basis method as a tool for developing emulators for equations with tunable parameters within the context of the nuclear many-body problem. The method uses a basis expansion informed by a set of solutions for a few…
We present the development of readout electronics and artificial-intelligence-based particle-identification methods for the SoLID Cherenkov detectors at Jefferson Lab. To operate in the high-rate, high-background SoLID environment, we…
Future space observatories dedicated to direct imaging and spectroscopy of extra-solar planets will require ultra-low-noise detectors that are sensitive over a broad range of wavelengths. Silicon charge-coupled devices (CCDs), such as…
Multimodal large language models are promising for clinical visual question answering tasks, but scaling to 3D imaging is hindered by high computational costs. Prior methods often rely on 2D slices or fixed-length token compression,…
Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying…
This dissertation attempts to drive innovation in the field of generative modeling for computer vision, by exploring novel formulations of conditional generative models, and innovative applications in images, 3D animations, and video. Our…
Large water Cherenkov detectors have shaped our current knowledge of neutrino physics and nucleon decay, and will continue to do so in the foreseeable future. These highly capable detectors allow for directional and topological, as well as…
This work introduces an advanced technique optimized for detecting photons generated by charged particles, leveraging Skipper-CCD sensors. By analyzing background sources and detection efficiencies, the technique achieves strong agreement…
Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be efficiently learned, generated, and generalized to new tasks. These have become foundational for…
Recently, transformer networks have outperformed traditional deep neural networks in natural language processing and show a large potential in many computer vision tasks compared to convolutional backbones. In the original transformer,…