Research map / Probabilistic and scientific modeling / Variational and generative sampling
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
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 |
|---|---|---|---|
| Increase decoder precision toward the near-deterministic regime | VAE on synthetic IMA conformal mixings · Synthetic Möbius mixings | MCC | Helped |
| Use a mixing outside the IMA class by applying a volume-preserving linear map | VAE on synthetic data · Synthetic Möbius mixings | MCC | Hurt |
| Train a VAE on sprites with four continuous factors selected to approximately satisfy IMA | VAE · Sprites | MCC | Helped |
Closest papers by meaning
- Variational Autoencoders Pursue PCA Directions (by Accident) (CVPR 2019 · similarity 0.91)
- The Autoencoding Variational Autoencoder (NeurIPS 2020 · similarity 0.91)
- Trading Information between Latents in Hierarchical Variational Autoencoders (ICLR 2023 · similarity 0.91)
- Consistency Regularization for Variational Auto-Encoders (NeurIPS 2021 · similarity 0.91)
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data (ICLR 2024 · similarity 0.89)
- Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders (ICML 2025 · similarity 0.89)
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.