REVIEW 19 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
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 19 Pith papers
-
CT-ScanGaze: A Dataset and Baselines for 3D Volumetric Scanpath Modeling
CT-ScanGaze, the first public eye-tracking dataset on CT volumes, contains 909 scans with radiologist gaze, reports, and findings, and CT-Searcher, a 3D scanpath model, beats adapted 2D baselines on it.
-
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.
-
DUDE: Diffusion-Based Unsupervised Cross-Domain Image Retrieval
A diffusion-based disentanglement method that separates object content from domain style achieves state-of-the-art unsupervised cross-domain image retrieval on three benchmarks.
-
RARR : Robust Real-World Activity Recognition with Vibration by Scavenging Near-Surface Audio Online
Pretraining a multitask VAE on online ASMR audio and finetuning only the activity head on vibration data improves cross-user activity recognition accuracy over baselines in a 4-participant study.
-
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.
-
Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner
Diffusion-completer training with a trajectory aligner makes diffusion-based auto-bidding work at scale, improving conversion value by 29.9% on a sparse public benchmark and by 2.0% in production at Kuaishou.
-
From Data to Decision: A Multi-Stage Framework for Class Imbalance Mitigation in Optical Network Failure Analysis
On experimental optical-network data, threshold adjustment improves failure-detection F1 by up to 15.3%, while CTGAN data augmentation improves failure-identification F1 by up to 24.2%.
-
Physical Layer Authentication Based on Hierarchical Variational Auto-Encoder for Industrial Internet of Things
A hierarchical autoencoder-plus-variational-autoencoder scheme authenticates industrial IoT transmitters from channel impulse responses, claiming higher F1 than three baselines without attacker channel priors.
-
Deciphering the Small-Angle Scattering of Polydisperse Hard Spheres using Deep Learning
A VAE trained on simulated small-angle scattering of polydisperse hard spheres generates scattering curves more accurately than Percus-Yevick theory and recovers volume fraction and polydispersity from test curves to ...
-
Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching
CGFM uses an auxiliary model's predictions as the source for flow matching to learn forecast residuals and improve time series forecasts.
-
Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigms
A status map of 2015-2025 learning-based motion planning in dynamic environments, organized by four roles learning can play: direct policy, classical-planner augmentation, hybrid coupling, and training support.
-
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.
-
Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
A survey reviewing how world models and agentic AI could be combined to give edge devices predictive, proactive decision-making, with a taxonomy of methods, applications, and challenges.
-
Comparing Normalizing Flows with Kernel Density Estimation in Estimating Risk of Automated Driving Systems
Normalizing flows fit scenario parameter densities better than KDE on held-out data, but produce roughly 40 times lower collision risk estimates, with no ground truth to decide which is correct.
-
Deep-Learning Investigation of Vibrational Raman Spectra for Plant-Stress Analysis
DIVA uses a variational autoencoder on first-derivative Raman spectra to cluster plant stress states and identify significant peaks without manual preprocessing.
-
Towards Foundation Auto-Encoders for Time-Series Anomaly Detection
A univariate VAE with dilated convolutions is proposed as a simple 'foundation' model for time-series anomaly detection, with preliminary zero-shot experiments on two datasets.
-
End to End Autoencoder MLP Framework for Sepsis Prediction
An autoencoder-MLP sepsis predictor achieves moderate accuracy on three ICU cohorts, but the autoencoder is trained only with classification loss, and reported gains over baselines lack error bars and may use test dat...
-
GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective
A position paper claiming that generative-AI agents that model and predict multi-agent dynamics will replace today's reactive MARL approaches.
-
A Survey on the Role of Artificial Intelligence and Machine Learning in 6G-V2X Applications
A brief survey of AI/ML methods for 6G-V2X communications, covering DL, RL, generative learning, and federated learning across four application areas.
Discussion (0). Sign in to comment.