{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hierarchical-vae-with-a-diffusion-based","title":"Hierarchical VAE with a Diffusion-based VampPrior","arxiv_id":"2412.01373","date":"2024-12-02","proceeding":null,"authors":["Anna Kuzina","Jakub M. Tomczak"],"abstract":"Deep hierarchical variational autoencoders (VAEs) are powerful latent variable generative models. In this paper, we introduce Hierarchical VAE with Diffusion-based Variational Mixture of the Posterior Prior (VampPrior). We apply amortization to scale the VampPrior to models with many stochastic layers. The proposed approach allows us to achieve better performance compared to the original VampPrior work and other deep hierarchical VAEs, while using fewer parameters. We empirically validate our method on standard benchmark datasets (MNIST, OMNIGLOT, CIFAR10) and demonstrate improved training stability and latent space utilization.","url_abs":"https://arxiv.org/abs/2412.01373v1","url_pdf":"https://arxiv.org/pdf/2412.01373v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hierarchical-vae-with-a-diffusion-based","repo_url":"https://github.com/akuzina/dvp_vae","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"hierarchical-vae","method_name":"Hierarchical VAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/density-estimation-on-cifar-10","task":"Density Estimation","dataset":"CIFAR-10","model":"DVP-VAE","rank_in_archive_order":5,"of":15,"metrics":{"NLL (bits/dim)":"2.73"},"uses_additional_data":false},{"leaderboard":"/sota/density-estimation-on-mnist","task":"Density Estimation","dataset":"MNIST","model":"DVP-VAE","rank_in_archive_order":5,"of":6,"metrics":{"NLL":"77.1"},"uses_additional_data":false},{"leaderboard":"/sota/density-estimation-on-omniglot","task":"Density Estimation","dataset":"OMNIGLOT","model":"DVp-VAE","rank_in_archive_order":3,"of":4,"metrics":{"NLL":"89.07"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.01373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01373"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/akuzina/dvp_vae","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"c582265b95a318a2","entry":"compute_z_L_size","repo":"akuzina/dvp_vae","repo_kind":"official","path":"run_experiment.py","file_url":"https://github.com/akuzina/dvp_vae/blob/HEAD/run_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c582265b95a318a2"}},{"code_sha256_prefix":"bbe43114e654718a","entry":"init_model","repo":"akuzina/dvp_vae","repo_kind":"official","path":"run_experiment.py","file_url":"https://github.com/akuzina/dvp_vae/blob/HEAD/run_experiment.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bbe43114e654718a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}