{"url":"/method/controlvae","slug":"controlvae","name":"ControlVAE","full_name":"ControlVAE","full_name_withheld":false,"description_markdown":"**ControlVAE** is a [variational autoencoder](https://paperswithcode.com/method/vae) (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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ControlVAE: Tuning, Analytical Properties, and Performance Analysis","paper":"/paper/controlvae-tuning-analytical-properties-and","first_author":"Huajie Shao","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/controlvae-tuning-analytical-properties-and"},"source":{"url":"https://arxiv.org/abs/2011.01754v1","title":"ControlVAE: Tuning, Analytical Properties, and Performance Analysis","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":null,"title":"ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters","date":"2022-10-12","arxiv_id":"2210.06063","n_code_links":0,"syntology":null},{"paper":null,"title":"Rethinking Controllable Variational Autoencoders","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/controlvae-tuning-analytical-properties-and","title":"ControlVAE: Tuning, Analytical Properties, and Performance Analysis","date":"2020-10-31","arxiv_id":"2011.01754","n_code_links":4,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/disentanglement","name":"Disentanglement","papers":2},{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/representation-learning","name":"Representation Learning","papers":2}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2020","papers":1},{"year":"2022","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/controlvae"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}