Normalizing Flows
PulseAugur coverage of Normalizing Flows — every cluster mentioning Normalizing Flows across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
Normalizing Flows Prove Capable for Continuous Control in RL
Researchers have demonstrated that normalizing flows (NFs) are capable models for continuous control tasks in reinforcement learning (RL). Contrary to the prevailing belief that NFs lack sufficient expressivity, this pa…
-
New Autoregressive Boltzmann Generators Leverage LLM Architectures for Molecular Sampling
Researchers have introduced Autoregressive Boltzmann Generators (ArBG), a new framework designed to improve the sampling of molecular systems at thermodynamic equilibrium. Unlike previous methods that relied on normaliz…
-
DeCoFlow tackles continual anomaly detection with novel NF decomposition
Researchers have developed DeCoFlow, a novel method for continual anomaly detection in industrial settings. This approach addresses the issue of catastrophic forgetting in Normalizing Flows (NFs) by decomposing subnets …
-
MIMFlow integrates Masked Image Modeling with Normalizing Flows for advanced image generation
Researchers have introduced MIMFlow, a novel framework that integrates Masked Image Modeling (MIM) with Normalizing Flows (NFs) for enhanced end-to-end image generation. This approach uses a VAE encoder to extract seman…
-
New framework tackles deconvolution and denoising for latent signals
Researchers have developed a new framework for nonparametric density deconvolution and empirical Bayes denoising, addressing the challenge of obscured latent signals in complex systems. The method utilizes a convolution…
-
Deep learning framework accelerates CO2 retrieval from satellite data
Researchers have developed a novel deep learning framework to more efficiently and accurately retrieve atmospheric carbon dioxide (CO2) data from NASA's Orbiting Carbon Observatory-2 (OCO-2) satellite. This new method u…
-
Review details AI models for inverse materials design
A new review paper details advancements in using generative models and multimodal learning for inverse materials design. It covers various generative model classes like VAEs, normalizing flows, and diffusion models, emp…
-
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 frameworks offer rigorous convergence certificates for Transport MCMC
Two new research papers introduce frameworks for certifying the convergence of Transport MCMC, a method that uses normalizing flows to improve Markov chain Monte Carlo sampling efficiency. The first paper, "Non-Vacuous …
-
SRC-Flow uses compact representations for image generation
Researchers have developed SRC-Flow, a novel method for image generation using normalizing flows. This approach addresses the challenge of high-dimensional representations in visual data by first compressing features in…
-
SRC-Flow method enhances image generation with compact semantic representations
Researchers have developed SRC-Flow, a new normalizing flow method designed to improve image generation quality. The approach addresses the challenge of normalizing flows struggling with high-dimensional representations…
-
New framework learns complex multiscale dynamics using normalizing flows
Researchers have developed a new data-driven framework to learn effective stochastic dynamics from limited observational data of complex multiscale systems. This approach models coupled stochastic differential equations…
-
Withdrawn paper proposed virtual targets for missile guidance
This paper, since withdrawn, proposed a novel method for many-vs-many missile guidance using virtual targets generated by a trajectory predictor. Instead of directly assigning interceptors to physical targets, the appro…
-
Apple advances normalizing flows, researchers explore denoising and state estimation
Apple Machine Learning Research has introduced iTARFlow, an advancement in Normalizing Flow generative models that maintains a likelihood-based objective and uses an iterative denoising procedure for sampling. This meth…
-
New generative models unify flows and achieve diffusion-level image quality
Researchers have developed a new generative modeling framework utilizing cumulative flow maps for long-range transport in probability space. This approach aims to connect local updates with finite-time transport, allowi…