{"id":35269899,"url":"https://github.com/zgbkdlm/gfk","last_synced_at":"2026-05-21T02:09:59.102Z","repository":{"id":296971540,"uuid":"879655262","full_name":"zgbkdlm/gfk","owner":"zgbkdlm","description":"Generative diffusion posterior sampling for informative likelihoods","archived":false,"fork":false,"pushed_at":"2025-06-03T06:05:15.000Z","size":384,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-03T17:59:50.123Z","etag":null,"topics":["diffusion-models","generative-model","guided-diffusion","posterior-sampling"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zgbkdlm.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-10-28T10:10:32.000Z","updated_at":"2025-06-03T06:05:16.000Z","dependencies_parsed_at":"2025-06-03T18:09:59.577Z","dependency_job_id":null,"html_url":"https://github.com/zgbkdlm/gfk","commit_stats":null,"previous_names":["zgbkdlm/gfk"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zgbkdlm/gfk","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zgbkdlm%2Fgfk","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zgbkdlm%2Fgfk/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zgbkdlm%2Fgfk/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zgbkdlm%2Fgfk/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zgbkdlm","download_url":"https://codeload.github.com/zgbkdlm/gfk/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zgbkdlm%2Fgfk/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33285137,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-20T15:12:43.734Z","status":"online","status_checked_at":"2026-05-21T02:00:07.181Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["diffusion-models","generative-model","guided-diffusion","posterior-sampling"],"created_at":"2025-12-30T11:59:31.455Z","updated_at":"2026-05-21T02:09:59.097Z","avatar_url":"https://github.com/zgbkdlm.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Generative diffusion posterior sampling for informative likelihoods\nThis implementation is associated with the paper \"Generative diffusion posterior sampling for informative likelihoods\" http://arxiv.org/abs/2506.01083. \nIn the paper we develop a new approach for conditional sampling of generative diffusion models with sequential Monte Carlo methods.\n\n\u003cimg src=\"./experiments/post.svg\" style=\"width: 80%; height: auto; display: block; margin-left: auto; margin-right: auto\"\u003e\n\n# Installation\nInstall the package via a standard procedure:\n\n```bash\ngit clone git@github.com:zgbkdlm/gfk.git\ncd gfk\npip install -e .\n```\n\nDepending on whether you need to run in a CPU/GPU, you may want to uninstall `jax`and `jaxlib` and then reinstall.\n\n# Reproduce experiments\nTo exactly reproduce the numbers and figures in the paper, first run experiments:\n\n```bash\ncd experiments\npython runs_gms/bash_aux.sh --dx=256 --nparticles=16384\npython runs_gms/bash_aux_noiseless.sh --dx=256 --nparticles=16384\npython runs_gms/bash_mcgdiff.sh --dx=256 --nparticles=16384\npython runs_gms/bash_wu.sh --dx=256 --nparticles=16384\n```\n\nThen, run the scripts in `./summary` to produce the tables and figures, e.g.,\n\n```bash\ncd experiements\npython ./summary/tabulate_gms.py\n```\n\nwill produce the table. \n\n# Citation\n```bibtex\n@article{Zhao2025b0smc, \n    author = {Zhao, Zheng}, \n    title = {Generative diffusion posterior sampling for informative likelihoods},\n    journal = {Communications in Information and Systems},\n    note = {Special issue for celebrating Thomas Kailath's 90th birthday}, \n    year = {2025},\n}\n```\n\n# Contact\nZheng Zhao, Linköping University, https://zz.zabemon.com.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzgbkdlm%2Fgfk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzgbkdlm%2Fgfk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzgbkdlm%2Fgfk/lists"}