No article text was recorded for this version.
unsupervised model selection (disentanglement evaluation gap)
Version 1 of 169 papers94 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Blog: DAVA: Disentangling Adversarial Variational Autoencoder
- Blog: Learning Disentangled Discrete Representations
- Blog: A Commentary on the Unsupervised Learning of Disentangled Representations
- Blog: A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
- Blog: Learning disentangled representations in the imaging domain
- Blog: Disentangling Factors of Variations Using Few Labels
- Blog: Disentangling by Factorising
- Blog: A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning.
- Blog: Review of Disentanglement Approaches for Medical Applications - Towards Solving the Gordian Knot of Generative Models in Healthcare
- Blog: Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback
- Blog: Where and What? Examining Interpretable Disentangled Representations
- Blog: Orthogonality-Enforced Latent Space in Autoencoders: An Approach to Learning Disentangled Representations
- Blog: Theory and Evaluation Metrics for Learning Disentangled Representations
- Blog: Learning Disentangled Representations with Latent Variation Predictability
- Blog: α-TCVAE: On the relationship between Disentanglement and Diversity
- Blog: Unsupervised Disentangled Representation Learning with Analogical Relations
- Blog: Disentangling by Factorising
- Blog: InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
- Blog: Identifying Ambiguous Similarity Conditions via Semantic Matching
- Blog: Disentanglement of Correlated Factors via Hausdorff Factorized Support
- Blog: Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness
- Blog: A Framework for the Quantitative Evaluation of Disentangled Representations
- Blog: Understanding Collapse in Non-contrastive Siamese Representation Learning
- Blog: Conditional Generation of Medical Images via Disentangled Adversarial Inference
- Blog: Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors
- Blog: On the DCI Framework for Evaluating Disentangled Representations: Extensions and Connections to Identifiability
- Blog: Review of Disentanglement Approaches for Medical Applications - Towards Solving the Gordian Knot of Generative Models in Healthcare
- Blog: Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedback
- Blog: Unsupervised Feature Learning for low-level Local Image Descriptors
- Blog: A Commentary on the Unsupervised Learning of Disentangled Representations
- Blog: Self-Supervised Enhancement of Latent Discovery in GANs
- Blog: Quantifying and Learning Linear Symmetry-Based Disentanglement
- Blog: Soft Matching Distance: A metric on neural representations that captures single-neuron tuning
- Blog: Unsupervised Model Selection for Variational Disentangled Representation Learning
- Blog: Robust Disentanglement of a Few Factors at a Time using rPU-VAE
- Blog: Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models
- Blog: Unsupervised Embedding Quality Evaluation
- Blog: Measuring disentangled generative spatio-temporal representation
- Blog: Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
- Blog: Measuring Orthogonality in Representations of Generative Models
- Blog: Unsupervised testing strategies for ASR
- Blog: Analyzing Text Representations by Measuring Task Alignment
- Blog: Unsupervised Disentangled Representation Learning with Analogical Relations
- Blog: Approaching an unknown communication system by latent space exploration and causal inference
- Blog: Isolating Sources of Disentanglement in Variational Autoencoders
- Blog: OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization
- Blog: Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
- Blog: beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
- Blog: Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
- Blog: A Tutorial on Learning Disentangled Representations in the Imaging Domain
- Blog: Analyzing Generative Models by Manifold Entropic Metrics
- Blog: A Metric for Linear Symmetry-Based Disentanglement
- Blog: Disentangling A Single MR Modality
- Blog: Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors
- Blog: Disentangling Learning Representations with Density Estimation
- Blog: Estimating class separability of text embeddings with persistent homology
- Blog: Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors
- Blog: Swapping Autoencoder for Deep Image Manipulation
- Blog: $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity
Showing 60 of 69 papers.
History & citation
Current · Permanent link
- Model Selection in Unsupervised Disentanglement merged into this direction (67% overlap)
- This direction split from Unsupervised Evaluation of Disentangled Representations (51% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_unsupervised_model_selection_disentangle_ca243d34,
title = {unsupervised model selection (disentanglement evaluation gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unsupervised-model-selection-disentanglement-evaluation-gap/rdr_ca243d3468484441ae617c2bf413f659},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_unsupervised_model_selection_disentangle_ca243d34_v1,
title = {unsupervised model selection (disentanglement evaluation gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unsupervised-model-selection-disentanglement-evaluation-gap/rdr_ca243d3468484441ae617c2bf413f659/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}