Related papers: Towards Foundation Models for Experimental Readout…
We propose a novel centrality definition-independent method for analyzing higher-order cumulants, specifically addressing the challenge of volume fluctuations that dominate in low-energy heavy-ion collisions. This method reconstructs…
Neuron segmentation from electron microscopy (EM) volumes is crucial for understanding brain circuits, yet the complex neuronal structures in high-resolution EM images present significant challenges. EM data exhibits unique characteristics…
A novel point cloud diffusion model for relativistic heavy-ion collisions, capable of ultra-fast generation of complete, event-by-event collision output, is introduced. When trained on UrQMD cascade simulations, the model generates…
Given a sequence of tokens, such as words, the task of next-token prediction is to predict the next-token conditional probability distribution. Decoder-only transformers have become effective models for this task, but their properties are…
The information content of atomic resolution scanning transmission electron microscopy (STEM) images can often be reduced to a handful of parameters describing each atomic column, chief amongst which is the column position. Neural networks…
Diffusion models have emerged as a promising approach for text generation, with recent works falling into two main categories: discrete and continuous diffusion models. Discrete diffusion models apply token corruption independently using…
We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. Motivated by recent work that predicts the probabilities of subsequent tokens using multiple heads, we…
Cherenkov detectors have been extensively developed and utilized in various scientific fields, including particle physics, astrophysics, and nuclear engineering. These detectors operate based on Cherenkov radiation, which is emitted when a…
A large area ring-imaging Cherenkov detector has been designed to provide clean hadron identification capability in the momentum range from 3 GeV/c up to 8 GeV/c for the CLAS12 experiments at the upgraded 12 GeV continuous electron beam…
Fission events from Special Nuclear Material (SNM), such as highly enriched uranium or plutonium, can produce simultaneous emission of multiple neutrons and high energy gamma-rays. The observation of time correlations between any of these…
We provide the first complete continuous time framework for denoising diffusion models of discrete data. This is achieved by formulating the forward noising process and corresponding reverse time generative process as Continuous Time Markov…
The quality of data representation in deep learning methods is directly related to the prior model imposed on the representations; however, generally used fixed priors are not capable of adjusting to the context in the data. To address this…
In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow…
The construction of predictive models of atomic nuclei from first principles is a challenging (yet necessary) task towards the systematic generation of theoretical predictions (and associated uncertainties) to support nuclear data…
We propose a novel approach that adapts hierarchical vision foundation models for real-time ultrasound image segmentation. Existing ultrasound segmentation methods often struggle with adaptability to new tasks, relying on costly manual…
We survey applications of pretrained foundation models in robotics. Traditional deep learning models in robotics are trained on small datasets tailored for specific tasks, which limits their adaptability across diverse applications. In…
Based on the predictive coding theory in neuroscience, we designed a bi-directional and recurrent neural net, namely deep predictive coding networks (PCN). It has feedforward, feedback, and recurrent connections. Feedback connections from a…
The electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. A natural choice to construct a model that yields transferable and linear-scaling predictions is to…
This article describes a new experimental method for accelerator based neutrino experiments called neutrino tagging. The method consists in exploiting the neutrino production mechanism, the $\pi^{\pm}\to\mu^{\pm}\nu_\mu$ decay, to…
Accurately predicting fluid dynamics and evolution has been a long-standing challenge in physical sciences. Conventional deep learning methods often rely on the nonlinear modeling capabilities of neural networks to establish mappings…