69 citations
- United States Naval Research LaboratoryUS9 papers
- Intel (United States)US8 papers
- MIT Computer Science and Artificial Intelligence LaboratoryUS8 papers
- Goddard Space Flight CenterUS5 papers
- University of California, BerkeleyUS5 papers
- Institut national de recherche en sciences et technologies du numériqueFR4 papers
- Massachusetts Institute of TechnologyUS4 papers
- United States Naval ObservatoryUS4 papers
- Lawrence Berkeley National LaboratoryUS3 papers
- New Mexico Institute of Mining and TechnologyUS3 papers
- SeabrookUS3 papers
- Adobe Systems (United States)US2 papers
30 papers
An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes
Alban Gauthier, Valentin Deschaintre, Alexandre Lanvin +3
Digital content creation is experiencing a profound change with the advent of deep generative models. For texturing, conditional image generators now allow the synthesis of realist…
Signal processing and data acquisition system for the BTO detectors onboard COSI
Shunsaku Nagasawa, Tadayuki Takahashi, Kazuhiro Nakazawa +15
The energy range from a few hundred keV to a few MeV includes important probes such as nuclear gamma-rays and the 511 keV annihilation line. However, compared to X-rays and GeV/TeV…
Optimized scintillation configuration for IMPISH hard x-ray detection
Dorcas D. Oseni, William S. Setterberg, Reed B. Masek +9
The Integrating Miniature Piggyback for Impulsive Solar Hard X-rays (IMPISH) is a solar X-ray spectrometer that features large-area scintillators, fast readout electronics, and goo…
Splat and Replace: 3D Reconstruction with Repetitive Elements
Nicolás Violante, Andreas Meuleman, Alban Gauthier +3
We leverage repetitive elements in 3D scenes to improve novel view synthesis. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly improved novel view synthe…
LFAR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models
Santiago Cuervo, Adel Moumen, Yanis Labrak +5
Text-pretrained language models (LMs) encode rich world knowledge, but adapting them to process and generate perceptual modalities such as audio and images while effectively levera…
Capacity, Technology Portfolios, and the Paradox of Concentration
Michele Fioretti, Junnan He, Jorge Tamayo
Does limiting the largest firm's capacity always lower prices? We model firms competing in supply schedules with multiple technologies, each with constant marginal cost up to capac…