{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IUY7P6GJPOX24RZLX4EHA22WH7","short_pith_number":"pith:IUY7P6GJ","schema_version":"1.0","canonical_sha256":"4531f7f8c97bafae472bbf08706b563ffd29fd3637aa69102483ea6613dc4537","source":{"kind":"arxiv","id":"2412.01169","version":2},"attestation_state":"computed","paper":{"title":"OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Aditya Grover, Akash Gokul, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Zichun Liao","submitted_at":"2024-12-02T06:13:01Z","abstract_excerpt":"We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to handle the joint distribution of multiple modalities. It outperforms previous any-to-any models on a wide range of tasks, such as text-to-image and text-to-audio synthesis. Our work offers three key contributions: First, we extend RF to a multi-modal setting and introduce a novel guidance mechanism, enabling users to flexibly control the alignment between d"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.01169","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-02T06:13:01Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"06512ccbbce79cc63e90af3045f3ec875f33f6eba47397c4276197e709522f49","abstract_canon_sha256":"393d2687d507802ca3acb423fee0b6f74924b755397b3c9065b49d884ea5e921"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:32.127723Z","signature_b64":"XmS8d2EeBEOGpw/5yhbCh70vSgmhAla51aO+CZyvz2DiwOwXnsypisa0pxaXzAW5PNUo7I+6Rp8PMb5CA1KMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4531f7f8c97bafae472bbf08706b563ffd29fd3637aa69102483ea6613dc4537","last_reissued_at":"2026-07-05T10:36:32.127147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:32.127147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Aditya Grover, Akash Gokul, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Zichun Liao","submitted_at":"2024-12-02T06:13:01Z","abstract_excerpt":"We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to handle the joint distribution of multiple modalities. It outperforms previous any-to-any models on a wide range of tasks, such as text-to-image and text-to-audio synthesis. Our work offers three key contributions: First, we extend RF to a multi-modal setting and introduce a novel guidance mechanism, enabling users to flexibly control the alignment between d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01169","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.01169/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.01169","created_at":"2026-07-05T10:36:32.127213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01169v2","created_at":"2026-07-05T10:36:32.127213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01169","created_at":"2026-07-05T10:36:32.127213+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUY7P6GJPOX2","created_at":"2026-07-05T10:36:32.127213+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUY7P6GJPOX24RZL","created_at":"2026-07-05T10:36:32.127213+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUY7P6GJ","created_at":"2026-07-05T10:36:32.127213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09622","citing_title":"Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7","json":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7.json","graph_json":"https://pith.science/api/pith-number/IUY7P6GJPOX24RZLX4EHA22WH7/graph.json","events_json":"https://pith.science/api/pith-number/IUY7P6GJPOX24RZLX4EHA22WH7/events.json","paper":"https://pith.science/paper/IUY7P6GJ"},"agent_actions":{"view_html":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7","download_json":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7.json","view_paper":"https://pith.science/paper/IUY7P6GJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01169&json=true","fetch_graph":"https://pith.science/api/pith-number/IUY7P6GJPOX24RZLX4EHA22WH7/graph.json","fetch_events":"https://pith.science/api/pith-number/IUY7P6GJPOX24RZLX4EHA22WH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7/action/storage_attestation","attest_author":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7/action/author_attestation","sign_citation":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7/action/citation_signature","submit_replication":"https://pith.science/pith/IUY7P6GJPOX24RZLX4EHA22WH7/action/replication_record"}},"created_at":"2026-07-05T10:36:32.127213+00:00","updated_at":"2026-07-05T10:36:32.127213+00:00"}