{"url":"/task/disentanglement","name":"Disentanglement","slug":"disentanglement","description_markdown":"This is an approach to solve a diverse set of tasks in a data efficient manner  by disentangling (or isolating ) the underlying structure of the main problem into disjoint parts of its representations.  This disentanglement can be done by focussing on the \"transformation\" properties of the world(main problem)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1854,"papers_with_code":744,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":13,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/disentanglement-on-kitti-masks","slug":"disentanglement-on-kitti-masks","dataset":"KITTI-Masks","dataset_url":"/dataset/kitti-masks","rows_in_archive":2,"metrics":["MCC"],"first_row_in_archive_order":{"model":"InfoNCE (Laplace, Box)","paper_title":"Contrastive Learning Inverts the Data Generating Process","paper_url":"/paper/contrastive-learning-inverts-the-data","paper_date":"2021-02-17","arxiv_id":"2102.08850","code_links":[{"title":"brendel-group/cl-ica","url":"https://github.com/brendel-group/cl-ica"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/disentanglement-on-3dident","slug":"disentanglement-on-3dident","dataset":"3DIdent","dataset_url":"/dataset/3dident","rows_in_archive":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"InfoNCE (Normal, Box)","paper_title":"Contrastive Learning Inverts the Data Generating Process","paper_url":"/paper/contrastive-learning-inverts-the-data","paper_date":"2021-02-17","arxiv_id":"2102.08850","code_links":[{"title":"brendel-group/cl-ica","url":"https://github.com/brendel-group/cl-ica"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/disentanglement-on-natural-sprites","slug":"disentanglement-on-natural-sprites","dataset":"Natural Sprites","dataset_url":"/dataset/natural-sprites","rows_in_archive":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"SlowVAE","paper_title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","paper_url":"/paper/towards-nonlinear-disentanglement-in-natural","paper_date":"2020-07-21","arxiv_id":"2007.10930","code_links":[{"title":"bethgelab/slow_disentanglement","url":"https://github.com/bethgelab/slow_disentanglement"}],"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/dsprites","name":"dSprites","full_name":"Disentanglement testing Sprites dataset","num_papers_in_archive":153},{"url":"/dataset/smallnorb","name":"smallNORB","full_name":"","num_papers_in_archive":112},{"url":"/dataset/sprites","name":"Sprites","full_name":"2D Video Game Character Sprites","num_papers_in_archive":52},{"url":"/dataset/3d-shapes-dataset","name":"3D Shapes Dataset","full_name":"","num_papers_in_archive":33},{"url":"/dataset/3d-cars","name":"3D Cars","full_name":"","num_papers_in_archive":22},{"url":"/dataset/causal3dident","name":"Causal3DIdent","full_name":"","num_papers_in_archive":12},{"url":"/dataset/mpi3d-disentanglement","name":"MPI3D Disentanglement","full_name":"","num_papers_in_archive":11},{"url":"/dataset/3dident","name":"3DIdent","full_name":"","num_papers_in_archive":10},{"url":"/dataset/fitness-aqa","name":"Fitness-AQA","full_name":"Fitness Action Quality Assessment [ECCV 2022]","num_papers_in_archive":3},{"url":"/dataset/kitti-masks","name":"KITTI-Masks","full_name":"","num_papers_in_archive":3},{"url":"/dataset/coil100-augmented","name":"Coil100-Augmented","full_name":"","num_papers_in_archive":1},{"url":"/dataset/natural-sprites","name":"Natural Sprites","full_name":"","num_papers_in_archive":1},{"url":"/dataset/xysquares","name":"XYSquares","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/representation-learning","name":"Representation Learning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":744,"tagged_in_all":1854,"items":[{"url":"/paper/a-style-based-generator-architecture-for","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","date":"2018-12-12","arxiv_id":"1812.04948","repositories_listed":83,"syntology":{"n":396,"n_ran":229,"n_unverified":167,"n_pointer_only":229}},{"url":"/paper/disentangling-by-factorising","title":"Disentangling by Factorising","date":"2018-02-16","arxiv_id":"1802.05983","repositories_listed":17,"syntology":{"n":24,"n_ran":13,"n_unverified":11,"n_pointer_only":6}},{"url":"/paper/adversarial-latent-autoencoders","title":"Adversarial Latent Autoencoders","date":"2020-04-09","arxiv_id":"2004.04467","repositories_listed":12,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/sigmoid-loss-for-language-image-pre-training","title":"Sigmoid Loss for Language Image Pre-Training","date":"2023-03-27","arxiv_id":"2303.15343","repositories_listed":11,"syntology":{"n":29,"n_ran":14,"n_unverified":15,"n_pointer_only":25}},{"url":"/paper/isolating-sources-of-disentanglement-in","title":"Isolating Sources of Disentanglement in Variational Autoencoders","date":"2018-02-14","arxiv_id":"1802.04942","repositories_listed":10,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/challenging-common-assumptions-in-the","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","date":"2018-11-29","arxiv_id":"1811.12359","repositories_listed":8,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/beta-vae-learning-basic-visual-concepts-with","title":"beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework","date":"2017-04-26","arxiv_id":null,"repositories_listed":6,"syntology":null},{"url":"/paper/leo-generative-latent-image-animator-for","title":"LEO: Generative Latent Image Animator for Human Video Synthesis","date":"2023-05-06","arxiv_id":"2305.03989","repositories_listed":5,"syntology":null},{"url":"/paper/learning-concise-representations-for","title":"Learning concise representations for regression by evolving networks of trees","date":"2018-07-03","arxiv_id":"1807.00981","repositories_listed":5,"syntology":null},{"url":"/paper/multiple-heads-are-better-than-one-few-shot","title":"Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts","date":"2021-04-02","arxiv_id":"2104.00887","repositories_listed":4,"syntology":null},{"url":"/paper/stylized-neural-painting","title":"Stylized Neural Painting","date":"2020-11-16","arxiv_id":"2011.08114","repositories_listed":4,"syntology":null},{"url":"/paper/controlvae-tuning-analytical-properties-and","title":"ControlVAE: Tuning, Analytical Properties, and Performance Analysis","date":"2020-10-31","arxiv_id":"2011.01754","repositories_listed":4,"syntology":null},{"url":"/paper/metrics-for-exposing-the-biases-of-content","title":"Measuring the Biases and Effectiveness of Content-Style Disentanglement","date":"2020-08-27","arxiv_id":"2008.12378","repositories_listed":4,"syntology":null},{"url":"/paper/disentangled-and-controllable-face-image","title":"Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning","date":"2020-04-24","arxiv_id":"2004.11660","repositories_listed":4,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/interpreting-the-latent-space-of-gans-for","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","date":"2019-07-25","arxiv_id":"1907.10786","repositories_listed":4,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/on-the-transfer-of-inductive-bias-from","title":"On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset","date":"2019-06-07","arxiv_id":"1906.03292","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/stylecrafter-enhancing-stylized-text-to-video","title":"StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter","date":"2023-12-01","arxiv_id":"2312.00330","repositories_listed":3,"syntology":{"n":23,"n_ran":16,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/prospect-expanded-conditioning-for-the","title":"ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models","date":"2023-05-25","arxiv_id":"2305.16225","repositories_listed":3,"syntology":{"n":13,"n_ran":12,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/versatile-diffusion-text-images-and","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","date":"2022-11-15","arxiv_id":"2211.08332","repositories_listed":3,"syntology":null},{"url":"/paper/disentangling-aesthetic-and-technical-effects","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","date":"2022-11-09","arxiv_id":"2211.04894","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/representation-topology-divergence-a-method-1","title":"Representation Topology Divergence: A Method for Comparing Neural Network Representations","date":"2021-12-31","arxiv_id":"2201.00058","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/volume-rendering-of-neural-implicit-surfaces","title":"Volume Rendering of Neural Implicit Surfaces","date":"2021-06-22","arxiv_id":"2106.12052","repositories_listed":3,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/disentangling-in-latent-space-by-harnessing-a","title":"Face Identity Disentanglement via Latent Space Mapping","date":"2020-05-15","arxiv_id":"2005.07728","repositories_listed":3,"syntology":null},{"url":"/paper/disentangling-physical-dynamics-from-unknown","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","date":"2020-03-03","arxiv_id":"2003.01460","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/weakly-supervised-disentanglement-without","title":"Weakly-Supervised Disentanglement Without Compromises","date":"2020-02-07","arxiv_id":"2002.02886","repositories_listed":3,"syntology":null},{"url":"/paper/mixnmatch-multifactor-disentanglement-and","title":"MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation","date":"2019-11-26","arxiv_id":"1911.11758","repositories_listed":3,"syntology":null},{"url":"/paper/variational-autoencoders-and-nonlinear-ica-a","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","date":"2019-07-10","arxiv_id":"1907.04809","repositories_listed":3,"syntology":{"n":17,"n_ran":11,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/deep-music-analogy-via-latent-representation","title":"Deep Music Analogy Via Latent Representation Disentanglement","date":"2019-06-09","arxiv_id":"1906.03626","repositories_listed":3,"syntology":null},{"url":"/paper/multiple-attribute-text-style-transfer","title":"Multiple-Attribute Text Style Transfer","date":"2018-11-01","arxiv_id":"1811.00552","repositories_listed":3,"syntology":null},{"url":"/paper/analyzing-assumptions-in-conversation","title":"A Large-Scale Corpus for Conversation Disentanglement","date":"2018-10-25","arxiv_id":"1810.11118","repositories_listed":3,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}