Related papers: Towards Designing and Exploiting Generative Networ…
We describe in these GLA2011 proceedings the software package LArSoft, a toolkit to perform simulation, analysis and reconstruction with the Liquid Argon (LAr) Time Projection Chambers (TPCs) within the US program of proposed detectors. We…
Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of…
MicroBooNE is a neutrino experiment located in the Booster Neutrino Beamline (BNB) at Fermilab, which collected data from 2015 to 2021. MicroBooNE's liquid argon time projection chamber (LArTPC) is accompanied by a photon detection system…
ArgoNeuT, a Liquid Argon Time Projection Chamber (LAr-TPC), has collected thousands of neutrino and anti-neutrino events between 0.1 and 10 GeV in the NuMI beamline at Fermilab (FNAL). Among other issues, the experiment will measure the…
Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor…
The paper is considering an opportunity for the CERN/GranSasso (CNGS) neutrino complex, concurrent time-wise with T2K and NOvA, to search for theta_13 oscillations and CP violation. Compared with large water Cherenkov (T2K) and fine grained…
The Time Projection Chamber (TPC) is an ideal candidate to finely study the charged particle ionization in a gaseous medium. Large volumes TPCs can be read out with a suitable number of channels offering a complete 3D reconstruction of an…
The Deep Underground Neutrino Experiment (DUNE) is a next generation long baseline (1300 km) neutrino oscillation experiment. The neutrino beam measurements will be performed by a near detector (ND) and far detector (FD). The far detector…
Neutrons are important final-state particles in neutrino interactions, yet they are not considered or reconstructed in most current neutrino LArTPC physics analyses. In this paper, we present a simulation-based proof-of-concept study of…
We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent…
The proliferation of generative image models has revolutionized AIGC creation while amplifying concerns over content provenance and manipulation forensics. Existing methods are typically either unable to localize tampering or restricted to…
In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of…
We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces…
Predicting future 3D LiDAR pointclouds is a challenging task that is useful in many applications in autonomous driving such as trajectory prediction, pose forecasting and decision making. In this work, we propose a new LiDAR prediction…
Cell motion and appearance have a strong correlation with cell cycle and disease progression. Many contemporary efforts in machine learning utilize spatio-temporal models to predict a cell's physical state and, consequently, the advancement…
Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…
In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…
For current and future neutrino oscillation experiments using large Liquid Argon Time Projection Chambers (LAr-TPCs), a key challenge is identifying neutrino interactions from the pervading cosmic-ray background. Rejection of such…
The MicroBooNE detector utilizes a liquid argon time projection chamber (LArTPC) with an 85 t active mass to study neutrino interactions along the Booster Neutrino Beam (BNB) at Fermilab. With a deployment location near ground level, the…
Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space…