Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
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 |
|---|---|---|---|
| Use CascadeVAE instead of JointVAE | Unsupervised discrete-factor inference · dSprites | classification accuracy: 44.79 (3.88) -> 78.84 (15.65) | Helped |
| Use CascadeVAE instead of JointVAE | Unsupervised discrete-factor inference · MNIST | classification accuracy: 78.33 (7.18) -> 84.19 (5.02) | Helped |
| Use CascadeVAE instead of JointVAE | Unsupervised discrete-factor inference · FashionMNIST | classification accuracy: 51.51 (4.42) -> 57.72 (3.29) | Helped |
| Add discrete variables and alternating discrete inference to CascadeVAE-C (ablation) | CascadeVAE · dSprites | disentanglement score: 81.69 (3.14) -> 91.34 (7.36) | Helped |
| Add information cascading to CascadeVAE-D (ablation) | CascadeVAE · dSprites | disentanglement score: 80.70 (4.77) -> 91.34 (7.36) | Helped |
| Add discrete variables to CascadeVAE-C (ablation) | CascadeVAE · dSprites | disentanglement score: 81.69 (3.14) -> 90.49 (5.28) | Helped |
| Add information cascading to CascadeVAE-D (ablation) | CascadeVAE · dSprites | disentanglement score: 79.67 (5.36) -> 90.49 (5.28) | Helped |
Closest papers by meaning
- Learning Disentangled Joint Continuous and Discrete Representations (NeurIPS 2018 · similarity 0.91)
- Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations (NeurIPS 2025 · similarity 0.87)
- Sequential Disentanglement by Extracting Static Information From A Single Sequence Element (ICML 2024 · similarity 0.87)
- Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models (NeurIPS 2024 · similarity 0.87)
- Disentangled Representation Learning via Flow Matching (NeurIPS 2026 · similarity 0.86)
- $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity (ICLR 2024 · similarity 0.86)
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.