conditional variational autoencoder
PulseAugur coverage of conditional variational autoencoder — every cluster mentioning conditional variational autoencoder across labs, papers, and developer communities, ranked by signal.
-
New CVAE method synthesizes shock time series from spectra
Researchers have developed a novel method for synthesizing shock time series waveforms from their corresponding shock response spectra (SRS) using conditional variational autoencoders (CVAEs). This approach extends prev…
-
New methods enable language-guided semantic editing of 3D Gaussian avatars
Two new research papers, ChromaGS and ManifoldSplat, introduce methods for semantically editing 3D Gaussian avatars using natural language. ChromaGS focuses on real-time color editing by augmenting Gaussian primitives w…
-
AI model accurately emulates stratospheric warming events
Researchers have developed a probabilistic deep learning emulator, specifically a ResNet-inspired Conditional Variational Autoencoder, to model the stochastic Holton--Mass model of stratospheric variability. This emulat…
-
AI model generates synthetic EV charging data to overcome privacy barriers
Researchers have developed a conditional variational autoencoder (CVAE) to generate synthetic electric vehicle (EV) charging session data. This method addresses the scarcity of real-world EV charging datasets due to pri…
-
SynthRCT framework generates synthetic 4DCT images for proton therapy robustness
Researchers have developed SynthRCT, a novel framework for generating synthetic 4D computed tomography (4DCT) images, which are crucial for evaluating the robustness of proton therapy treatment plans. This conditional g…
-
Machine learning reconstructs shock time series from spectral data
Researchers have developed a conditional variational autoencoder (CVAE) to reconstruct shock time series from shock response spectrum (SRS) curves. This machine learning approach offers a data-driven inverse mapping, ov…
-
AI pipeline generates automotive panel designs meeting performance targets
Researchers have developed a novel two-stage pipeline for the inverse design problem of automotive hood inner panels, aiming to generate geometries that meet specific performance requirements. The first stage identifies…
-
New CBOL-Tuner framework optimizes particle accelerator tuning using AI
Researchers have developed a novel framework called CBOL-Tuner to optimize complex dynamical systems like particle accelerators. This method efficiently explores a high-dimensional latent space by integrating a conditio…
-
New framework enhances lightweight models for robotic control
Researchers have developed XS-VLA, a novel two-stage framework designed to enhance robotic control using lightweight vision-language models. The framework addresses the limitations of large models in real-time applicati…
-
New Bayesian framework evaluates scenario compatibility in generative population synthesis
Researchers have developed a new Bayesian framework to evaluate the compatibility of scenario targets within generative population synthesis models. This framework utilizes a population-aware conditional variational aut…
-
AI model predicts diverse human movement goals using CVAE
Researchers have developed a new method for predicting diverse human movement goals using a conditional variational autoencoder (CVAE). This approach leverages environmental context and human pose to generate multiple p…
-
New AI framework enhances flood mapping with satellite imagery · 2 sources tracked
Researchers have developed a new framework for high-resolution flood mapping using Sentinel-1 and Sentinel-2 satellite imagery. This approach addresses limitations such as cloud cover in optical data and speckle noise i…
-
New Attention Model Handles Missing Modalities in Robot Learning
Researchers have developed a new attention-based multimodal model designed to handle situations where some sensor data is missing during both training and inference. This model, formulated as a conditional variational a…