Normalizing Flow
PulseAugur coverage of Normalizing Flow — every cluster mentioning Normalizing Flow across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New framework protects semantic privacy in 3D point clouds
Researchers have developed a new framework for protecting semantic privacy in 3D point cloud data. This method aims to conceal original class information while maintaining utility for downstream tasks and allowing autho…
-
New research paper details "prior laundering" in Bayesian inverse problems
A new research paper introduces the concept of "prior laundering," a technique where learned generative priors are used for ill-posed Bayesian inverse problems. This method involves using an archive of legacy reconstruc…
-
Generative AI and Transfer Learning Enhance Surrogate Modeling for Engineering
Researchers have developed a novel framework for probabilistic multi-fidelity surrogate modeling that leverages generative AI and transfer learning to address data scarcity in complex engineering systems. The approach u…
-
Visual MAE adapted for time series anomaly detection
Researchers have developed VAN-AD, a novel framework for time series anomaly detection that adapts a visual Masked Autoencoder (MAE) pretrained on ImageNet. This approach aims to improve generalization capabilities acro…
-
AI estimates food material properties using reinforcement learning
Researchers have developed a novel approach using latent space reinforcement learning to estimate material properties in food fracture simulations, specifically demonstrated with orange peeling. This method trains a goa…
-
New particle method slashes Bayesian inference costs
Researchers have developed amortized mean-shift interacting particles, a novel method for Bayesian inference that significantly reduces the computational cost of evaluating integrals in inverse problems. Unlike traditio…
-
New FTIP method enhances Bayesian function-space inference
Researchers have introduced Flow-Transformed Implicit Processes (FTIP), a novel variational inference method designed to enhance Bayesian function-space modeling. FTIP addresses limitations in existing approaches by emp…
-
New methods enhance conformal prediction for uncertainty quantification
Researchers have developed novel methods for conformal prediction, a technique used for uncertainty quantification in machine learning. The first approach utilizes a differentiable nonconformity score to create a flow o…
-
New discriminator-informed resampling improves Gaussian mixture filter accuracy
Researchers have developed a new method to improve the Ensemble Gaussian Mixture Filter (EnGMF) by incorporating a learned discriminator for the resampling step. This discriminator, implemented using a normalizing flow …
-
Researchers use generative modeling to solve quantum dynamics via score matching
Researchers have developed a novel method to solve the time-dependent Schrödinger equation by learning the score function on Bohmian trajectories. This approach utilizes a neural network to parametrize the score and min…