Methods › Computer Vision › Generative Models › ControlVAE
ControlVAE
Introduced by Huajie Shao et al. in ControlVAE: Tuning, Analytical Properties, and Performance Analysis
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ControlVAE is a variational autoencoder (VAE) framework that combines the automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value. It leverages a non-linear PI controller, a variant of the proportional-integral-derivative (PID) control, to dynamically tune the weight of the KL-divergence term in the evidence lower bound (ELBO) using the output KL-divergence as feedback. This allows for control of the KL-divergence to a desired value (set point), which is effective in avoiding posterior collapse and learning disentangled representations.
Papers archive 2025-07-28
3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters 12 Oct 2022 · 0 repositories · arXiv:2210.06063
-
Rethinking Controllable Variational Autoencoders 1 Jan 2022 · 0 repositories
-
ControlVAE: Tuning, Analytical Properties, and Performance Analysis 31 Oct 2020 · 4 repositories · arXiv:2011.01754
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Disentanglement | 2 |
| Image Generation | 2 |
| Language Modeling | 2 |
| Language Modelling | 2 |
| Representation Learning | 2 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections