No article text was recorded for this version.
disentanglement-reconstruction trade-off
Version 2 of 2379 papers484 conceptsfrozen 2026-10-04
Papers in this version
- Blog: beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
- Blog: Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language
- Blog: Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation
- Blog: Review of Disentanglement Approaches for Medical Applications - Towards Solving the Gordian Knot of Generative Models in Healthcare
- Blog: Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion
- Blog: Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
- Blog: Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis
- Blog: A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations
- Blog: Metrics for Exposing the Biases of Content-Style Disentanglement
- Blog: Variational Autoencoders with Decremental Information Bottleneck for Disentanglement
- Blog: A Closer Look at Disentangling in β-VAE
- Blog: On the Adversarial Robustness of Generative Autoencoders in the Latent Space
- Blog: Learning Interpretable Disentangled Representations Using Adversarial VAEs
- Blog: PRI-VAE: Principle-of-Relevant-Information Variational Autoencoders
- Blog: Early Visual Concept Learning with Unsupervised Deep Learning
- Blog: Pythae: Unifying Generative Autoencoders in Python - A Benchmarking Use Case
- Blog: Disentanglement Challenge: From Regularization to Reconstruction
- Blog: Disentangling Factors of Variation by Mixing Them
- Blog: On Disentanglement and Mutual Information in Semi-Supervised Variational Auto-Encoders
- Blog: Beta-VAE Reproducibility: Challenges and Extensions
- Blog: Forget-me-not! Contrastive Critics for Mitigating Posterior Collapse
- Blog: On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation
- Blog: The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited
- Blog: EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
- Blog: Diversity vs. Recognizability: Human-like generalization in one-shot generative models
- Blog: From data to functa: Your data point is a function and you can treat it like one
- Blog: Learning to Manipulate Individual Objects in an Image
- Blog: Disentanglement with factor quantized variational autoencoders
- Blog: An Introduction to Deep Generative Modeling
- Blog: Inductive Biases for Disentangled Representation Learning with Correlated Treatment--Nuisance Factors
- Blog: Generative Visual Image Understanding Based on Disentangled Representation Learning
- Blog: Moment Matching Deep Contrastive Latent Variable Models
- Blog: Learning Disentangled Representation with Pairwise Independence
- Blog: Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
- Blog: An Image is Worth More Than a Thousand Words: Towards Disentanglement in The Wild
- Blog: Learning to Manipulate Individual Objects in an Image
- Blog: A Bayesian Nonparametrics View into Deep Representations
- Blog: Theory and Evaluation Metrics for Learning Disentangled Representations
- Blog: Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
- Blog: Improving Disentangled Representation Learning with the Beta Bernoulli Process
- Blog: Are VAEs Bad at Reconstructing Molecular Graphs?
- Blog: Towards A Controllable Disentanglement Network
- Blog: Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective
- Blog: Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI
- Blog: Aligning Latent Spaces with Flow Priors
- Blog: Fader Networks: Manipulating Images by Sliding Attributes
- Blog: Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
- Blog: Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement
- Blog: Geometric Disentanglement for Generative Latent Shape Models
- Blog: Learning Disentangled Representations with Wasserstein Auto-Encoders
- Blog: Adversarial Disentanglement with Grouped Observations
- Blog: Capturing Label Characteristics in VAEs
- Blog: A Survey on Variational Autoencoders from a Green AI Perspective
- Blog: Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings
- Blog: Learning Hierarchical Features from Deep Generative Models
- Blog: On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation
- Blog: Dis-AE: Multi-domain & Multi-task Generalisation on Real-World Clinical Data
- Blog: Improving Disentangled Representation Learning with the Beta Bernoulli Process
- Blog: Interaction Modeling with Multiplex Attention
- Blog: Improving the Diffusability of Autoencoders
Showing 60 of 379 papers.
History & citation
Current · Permanent link
- Progressive Information Capacity for Disentangled Representations merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_disentanglement_reconstruction_trade_off_aa2e32c4,
title = {disentanglement-reconstruction trade-off},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/disentanglement-reconstruction-trade-off/rdr_aa2e32c464b942a8a829aa89b8694032},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_disentanglement_reconstruction_trade_off_aa2e32c4_v2,
title = {disentanglement-reconstruction trade-off},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/disentanglement-reconstruction-trade-off/rdr_aa2e32c464b942a8a829aa89b8694032/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}