{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YBVDP2Y62YSG3XUMKHY4YR54RI","short_pith_number":"pith:YBVDP2Y6","schema_version":"1.0","canonical_sha256":"c06a37eb1ed6246dde8c51f1cc47bc8a3ce2966e869b8334fe891e141ec20cad","source":{"kind":"arxiv","id":"2407.17571","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Models For Multi-Modal Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Belinda Zeng, Benjamin Z. Yao, Bunyamin Sisman, Changyou Chen, Han Ding, Ouye Xie, Son Dinh Tran, Yi Xu","submitted_at":"2024-07-24T18:04:17Z","abstract_excerpt":"Diffusion-based generative modeling has been achieving state-of-the-art results on various generation tasks. Most diffusion models, however, are limited to a single-generation modeling. Can we generalize diffusion models with the ability of multi-modal generative training for more generalizable modeling? In this paper, we propose a principled way to define a diffusion model by constructing a unified multi-modal diffusion model in a common diffusion space. We define the forward diffusion process to be driven by an information aggregation from multiple types of task-data, e.g., images for a gene"},"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":"2407.17571","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T18:04:17Z","cross_cats_sorted":[],"title_canon_sha256":"ab070fccd86566f384d19c6a933fc3007bca5eefe5530a4bf387c690a0577ed2","abstract_canon_sha256":"f80a38e1549ee74cd6e5f91cdb74e31fb697c5da4fb723d297cc6a70c8bc9d2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:28.173310Z","signature_b64":"GQbMK906UJZ0ARrN4MX5sce3R+mkL7vOuJvn2AvHXf5pQuuhV61QLuj8lIWROdUQfgpxsYTdolaylO83mcAEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c06a37eb1ed6246dde8c51f1cc47bc8a3ce2966e869b8334fe891e141ec20cad","last_reissued_at":"2026-07-05T09:11:28.172845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:28.172845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Models For Multi-Modal Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Belinda Zeng, Benjamin Z. Yao, Bunyamin Sisman, Changyou Chen, Han Ding, Ouye Xie, Son Dinh Tran, Yi Xu","submitted_at":"2024-07-24T18:04:17Z","abstract_excerpt":"Diffusion-based generative modeling has been achieving state-of-the-art results on various generation tasks. Most diffusion models, however, are limited to a single-generation modeling. Can we generalize diffusion models with the ability of multi-modal generative training for more generalizable modeling? In this paper, we propose a principled way to define a diffusion model by constructing a unified multi-modal diffusion model in a common diffusion space. We define the forward diffusion process to be driven by an information aggregation from multiple types of task-data, e.g., images for a gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17571","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/2407.17571/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":"2407.17571","created_at":"2026-07-05T09:11:28.172905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17571v2","created_at":"2026-07-05T09:11:28.172905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17571","created_at":"2026-07-05T09:11:28.172905+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBVDP2Y62YSG","created_at":"2026-07-05T09:11:28.172905+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBVDP2Y62YSG3XUM","created_at":"2026-07-05T09:11:28.172905+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBVDP2Y6","created_at":"2026-07-05T09:11:28.172905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07903","citing_title":"Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI","json":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI.json","graph_json":"https://pith.science/api/pith-number/YBVDP2Y62YSG3XUMKHY4YR54RI/graph.json","events_json":"https://pith.science/api/pith-number/YBVDP2Y62YSG3XUMKHY4YR54RI/events.json","paper":"https://pith.science/paper/YBVDP2Y6"},"agent_actions":{"view_html":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI","download_json":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI.json","view_paper":"https://pith.science/paper/YBVDP2Y6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17571&json=true","fetch_graph":"https://pith.science/api/pith-number/YBVDP2Y62YSG3XUMKHY4YR54RI/graph.json","fetch_events":"https://pith.science/api/pith-number/YBVDP2Y62YSG3XUMKHY4YR54RI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI/action/storage_attestation","attest_author":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI/action/author_attestation","sign_citation":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI/action/citation_signature","submit_replication":"https://pith.science/pith/YBVDP2Y62YSG3XUMKHY4YR54RI/action/replication_record"}},"created_at":"2026-07-05T09:11:28.172905+00:00","updated_at":"2026-07-05T09:11:28.172905+00:00"}