REVIEW 27 cited by
Tutorial on Variational Autoencoders
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
Tutorial on Variational Autoencoders
read the original abstract
In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function approximators (neural networks), and can be trained with stochastic gradient descent. VAEs have already shown promise in generating many kinds of complicated data, including handwritten digits, faces, house numbers, CIFAR images, physical models of scenes, segmentation, and predicting the future from static images. This tutorial introduces the intuitions behind VAEs, explains the mathematics behind them, and describes some empirical behavior. No prior knowledge of variational Bayesian methods is assumed.
Forward citations
Cited by 27 Pith papers
-
Panel Flow Matching: A Generative Approach to Learning Distributions of Longitudinal Data
Panel Flow Matching is a generative method to estimate panel densities from longitudinal data with statistical guarantees under irregular sampling, supporting completion, synthetic data, and classification.
-
CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors
CoFi-UCGen achieves both coarse- and fine-grained unsupervised conditional image generation by using bit-codes for structured latent space and hierarchical modulation in diffusion models.
-
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
Markov chain Phase-Type decoders in VAEs overcome the structural inability of Gaussian-Lipschitz models to produce heavy-tailed outputs, cutting tail KS distance by up to 6x and extreme quantile error by up to 10x on ...
-
TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics
TacticGen generates realistic, adaptable football tactics via a multi-agent diffusion transformer trained on 3.3M events and 100M frames, supporting rule-, language-, or model-based guidance at inference time.
-
Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder
A PI-GCVAE with a differentiable eigenvalue decoder and Gaussian-copula latents recovers true stiffness posteriors on noisy synthetic short-span bridge data at ~79% 95%-coverage.
-
A Semi-Supervised Variational Autoencoder for Generating Neutron Star Equations of State
A semi-supervised VAE trained on Skyrme EOS data reconstructs equations of state with mean absolute percentage errors under 0.14% using two supervised observables (M_max, R_1.4) and one variational latent variable.
-
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...
-
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generali...
-
Stability Enhanced Gaussian Process Variational Autoencoders
SEGP-VAE learns stable low-dimensional LTI systems from video data by deriving GP mean and covariance from LTI equations and using a complete unconstrained parametrization of semi-contracting systems.
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
-
LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning
LEGO selects CVAE training targets from bottleneck regions on near-optimal paths and ensures diversity across regions, with formal definitions and performance guarantees.
-
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
Markov chain Phase-Type decoders in VAEs enable heavy-tailed generation where Gaussian decoders fail due to structural limitations from Lipschitz continuity.
-
A dimensional R2 regression metric
Dim-R2 extends R2 to arbitrary dimensions, supplies multidimensional accuracy views, and reduces noise sensitivity for better regression evaluation.
-
Learning Probabilistic Responsibility Allocations for Multi-Agent Interactions
A CVAE-based approach learns distributions over responsibility allocations in multi-agent scenes by grounding them in induced controls through differentiable optimization, showing strong prediction on driving data.
-
Causal Transfer in Medical Image Analysis
Causal Transfer Learning unifies structural causal models, invariant risk minimisation and counterfactuals with transfer learning to produce domain-robust medical image models.
-
Drivetrain simulation using variational autoencoders
Variational autoencoders generate jerk signals from torque inputs in electric drivetrains and outperform physics-based baselines without detailed parametrization.
-
Variational meta-learning inference for low dimensional neural system identification
A variational (VAE-style) extension of manifold meta-learning that adds Laplace-approximation uncertainty bounds to low-data nonlinear system identification.
-
Cross-scale spatially-aware generative modeling of transcriptomic programs underlying neurodegenerative brain organization
A variational generative model with graph-based spatial regularization predicts Alzheimer's-related cortical thinning from transcriptomic profiles across 68 regions, reporting explained variance of 0.8604 and spatial ...
-
Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
Auto-encoder approximates SEOBNRv4 waveforms for four-parameter aligned-spin binaries, delivering 4 orders of magnitude speedup at median mismatch of 10^{-2}.
-
WriterForcing: Generating more interesting story endings
WriterForcing combines keyphrase attention and non-generic word promotion in Seq2Seq models to produce more diverse and interesting story endings.
-
Neural Embedding for Physical Manipulations
Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.
-
To each route its own ETA: A generative modeling framework for ETA prediction
A route-specific deep generative model learns the probability distribution of bus trip ETAs from historical data alone and conditions updates on real-time trip progress.
-
On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data
Extends Social-STGCNN with CVAE for multimodal trajectory prediction and reports moderate gains plus better diversity on ETH/UCY benchmarks and robot data.
-
Enhancing Malware Detection with Generative AI: Using Variational Autoencoders to Boost Machine Learning Classifiers' Performance
VAEs generate synthetic malware to augment datasets, yielding reported gains in accuracy, precision, recall, and F1 for three ML classifiers.
-
Representation learning from OCT images
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.
-
A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models
A structured survey of audio bandwidth extension that organizes the transition from deterministic discriminative DNNs to generative approaches including GANs, diffusion models, and flow-based methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.