REVIEW 17 cited by
Glow: Generative Flow with Invertible 1x1 Convolutions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this paper we propose Glow, a simple type of generative flow using an invertible 1x1 convolution. Using our method we demonstrate a significant improvement in log-likelihood on standard benchmarks. Perhaps most strikingly, we demonstrate that a generative model optimized towards the plain log-likelihood objective is capable of efficient realistic-looking synthesis and manipulation of large images. The code for our model is available at https://github.com/openai/glow
Forward citations
Cited by 17 Pith papers
-
Autoregressive Boltzmann Generators
ArBG replaces flow-based methods with autoregressive models for Boltzmann sampling, showing gains on peptide benchmarks and a 132M-parameter model Robin cutting zero-shot energy error by over 60% on 8-residue systems.
-
Guided Image Generation with Conditional Invertible Neural Networks
Proposes cINN architecture for conditional image generation that by construction yields diverse sharp samples, demonstrated on MNIST digit generation and image colorization with latent space manipulation.
-
Probabilistic redshift estimation of unresolved galaxies from multi-band background light maps
Conditional normalising flows trained on mock multi-band images recover the redshift distribution of unresolved galaxies with sub-percent accuracy in mean and width, under idealized simulation-matched conditions.
-
Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
Physics-informed Transformer encodings plus conditional normalizing flows yield sharper, better-calibrated posteriors for eccentric BBHs in white-noise PTA data than physics-agnostic SBI baselines.
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
End-to-end masked-image VAE plus normalizing flow yields FID 2.50 on ImageNet 256 with 128 tokens and higher linear-probe accuracy than unmasked counterparts.
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
MIMFlow uses a VAE on masked images to feed semantic latents to a normalizing flow while a decoder handles high-frequency details, reporting FID 2.50 and 71.3% linear probing on ImageNet 256x256 with 128 tokens.
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
MIMFlow is an end-to-end model that routes semantic latents through a normalizing flow while a decoder handles high-frequency pixels, reporting FID 2.50 and 71.3% linear probing accuracy on ImageNet 256x256 with 128 tokens.
-
Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions
Generative models for cosmological field-level inference can reproduce posterior means and cross-correlations yet fail to capture correct uncertainty geometry when validated against HMC reference samples.
-
Study of jet-induced hydro response in high-energy heavy-ion collisions with a flow-matching generative model
A conditional flow-matching model trained on CoLBT-hydro reproduces marginal γ-jet medium-response hadron spectra in 0–10% Pb+Pb at 5.02 TeV with ~10⁶× speedup while preserving front and diffusion-wake statistics.
-
Study of jet-induced hydro response in high-energy heavy-ion collisions with a flow-matching generative model
A flow-matching generative model trained on CoLBT-hydro data conditionally generates marginal final-state hadron spectra from jet-induced hydro responses in 0-10% Pb+Pb collisions at 5.02 TeV, matching training data s...
-
Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database
DSEE is a flow-based emulator that generates stellar evolution tracks and isochrones as probabilistic outputs from a single model trained on millions of simulations, enabling fast interpolation and uncertainty-aware analyses.
-
Reversible Deep Learning for 13C NMR in Chemoinformatics: On Structures and Spectra
A conditional invertible neural network unifies forward prediction of 13C NMR spectra from structures and inverse generation of structure candidates from spectra.
-
Analytic Bijections for Smooth and Interpretable Normalizing Flows
Three new analytic bijections and a radial flow architecture give globally smooth, closed-form invertible normalizing flows that match or beat spline baselines on benchmarks and improve phi^4 lattice-field sampling.
-
VideoGPT: Video Generation using VQ-VAE and Transformers
VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.
-
Joint Flow Matching for Generator-Consistent Classification
Assigning images and labels opposite endpoints in a flow gives one model that both generates and classifies, with forward and backward passes sampling from the same joint.
-
Unsupervised Susceptibility Distortion Correction of EPI without Calibration Scans via Image Translation-Based Registration
SACRED performs unsupervised susceptibility distortion correction of EPI fMRI via image translation-based registration between T1w and unidirectional BOLD images, with test-time adaptation for robustness.
-
Replicating weak-lensing summary-statistic covariances with normalizing flows
Normalizing flows trained on weak-lensing convergence maps reproduce mean and variance of summary statistics to percent level but underestimate off-diagonal covariance by up to 25% unless data augmentation and noise i...
Discussion (0). Sign in to comment.