Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Disentangled Joint Continuous and Discrete Representations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Control continuous and discrete channel capacities separately | JointVAE · MNIST | disentanglement | Helped |
| Use a joint continuous and discrete latent distribution without changing the loss (ablation) | β-VAE · Joint continuous and discrete representations | disentanglement | Hurt |
| Use a higher β on the continuous KL term and a lower β on the discrete KL term (ablation) | β-VAE · Joint continuous and discrete representations | disentanglement | Mixed |
| Approximate the Gumbel-Softmax KL with categorical KL estimates (ablation) | β-VAE with Gumbel-Softmax latents · Joint continuous and discrete representations | learning stability | Hurt |
| Use a total capacity increase rather than separate continuous and discrete capacities (ablation) | JointVAE · Joint continuous and discrete representations | disentanglement | Hurt |
Closest papers by meaning
- Learning Discrete and Continuous Factors of Data via Alternating Disentanglement (ICML 2019 · similarity 0.91)
- Variational Inference of Disentangled Latent Concepts from Unlabeled Observations (ICLR 2018 · similarity 0.91)
- Disentangling Disentanglement in Variational Autoencoders (ICML 2019 · similarity 0.91)
- Disentangling by Factorising (ICML 2018 · similarity 0.90)
- Disentangled Representation Learning via Flow Matching (NeurIPS 2026 · similarity 0.89)
- Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.