{"paper":{"title":"Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"One-step generative models recover key galaxy morphology statistics from redshift-conditioned images at orders-of-magnitude lower cost than standard diffusion sampling.","cross_cats":["astro-ph.GA","cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Sandro Tacchella, Tianyue Yang, Xiao Xue","submitted_at":"2026-05-17T17:00:39Z","abstract_excerpt":"Understanding galaxy morphology evolution across cosmic time requires models that can generate realistic galaxy populations conditioned on redshift. In this work, we study efficient redshift-conditioned generative modeling for astrophysical image synthesis using diffusion models and pixel-MeanFlow. We first review the connections between score-based diffusion models, Flow Matching, one-step generative models, and modern diffusion samplers. We then evaluate DDPM, DDIM, DEIS-AB2, DPM++2M, and one-step pixel-MeanFlow on the GalaxiesML-64 dataset using morphology-based metrics, including elliptici"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results demonstrate that one-step generative models can recover key galaxy morphology statistics at orders-of-magnitude lower computational cost, opening a path toward efficient conditional simulators for large cosmological surveys and simulation-based scientific inference.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen morphology-based metrics (ellipticity, semi-major axis, Sérsic index, isophotal area) are sufficient proxies for the scientific usefulness of the generated images in downstream cosmological analyses and inference tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"One-step generative models recover key galaxy morphology statistics from redshift-conditioned images at orders-of-magnitude lower cost than standard diffusion sampling.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"df2ff0445a19c57cbb13e17d42ad21a48eb72a678f4533919eac46ff6fd43d4f"},"source":{"id":"2605.17546","kind":"arxiv","version":1},"verdict":{"id":"e8da3c4f-b71e-4e06-9b91-5dc4e530ec00","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T22:06:16.778874Z","strongest_claim":"Our results demonstrate that one-step generative models can recover key galaxy morphology statistics at orders-of-magnitude lower computational cost, opening a path toward efficient conditional simulators for large cosmological surveys and simulation-based scientific inference.","one_line_summary":"One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen morphology-based metrics (ellipticity, semi-major axis, Sérsic index, isophotal area) are sufficient proxies for the scientific usefulness of the generated images in downstream cosmological analyses and inference tasks.","pith_extraction_headline":"One-step generative models recover key galaxy morphology statistics from redshift-conditioned images at orders-of-magnitude lower cost than standard diffusion sampling."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17546/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.587669Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:12:23.523658Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.609852Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.544814Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d2b60c7b788edf70618232f4a75bff82b6d669e2c99fc483c791b752aa007bd5"},"references":{"count":65,"sample":[{"doi":"10.1088/0067-0049/203/2/21","year":2012,"title":"doi:10.1088/0067-0049/203/2/21 , eid =","work_id":"fadc132a-8102-44bc-b4cb-27d7b24e86fb","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1103/physrevd.105","year":2022,"title":"Accurate effective fluid approximation for ultralight axions","work_id":"977bbb6e-26ea-4a34-a487-d6a6c5e043bf","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1051/0004-6361/201834918","year":2019,"title":"2019, A&A, 625, A2, doi:10.1051/0004-6361/201834918","work_id":"bf849814-d0b5-4d98-ab27-110ef6070810","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Second data release of the Hyper Suprime-Cam Subaru Strategic Program","work_id":"17306f27-2942-4e0a-809f-0697d3ba98a4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"arXiv e-prints , keywords =","work_id":"f6113be7-4227-4b07-b837-4fba8bc98567","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":65,"snapshot_sha256":"5728b07909cf3d171803596b273ff3dd9840df8919d18cbcc1473f89049cfea4","internal_anchors":15},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}