{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OSXLWJWWC3R77YEEMFDYCD62RE","short_pith_number":"pith:OSXLWJWW","schema_version":"1.0","canonical_sha256":"74aebb26d616e3ffe0846147810fda89007093ba0d8b3f72949f2baa7840a260","source":{"kind":"arxiv","id":"2506.07848","version":1},"attestation_state":"computed","paper":{"title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Qinglin Lu, Ran Yi, Teng Hu, Yuan Zhou, Zhengguang Zhou, Zhentao Yu","submitted_at":"2025-06-09T15:11:09Z","abstract_excerpt":"Despite recent advances in video generation, existing models still lack fine-grained controllability, especially for multi-subject customization with consistent identity and interaction. In this paper, we propose PolyVivid, a multi-subject video customization framework that enables flexible and identity-consistent generation. To establish accurate correspondences between subject images and textual entities, we design a VLLM-based text-image fusion module that embeds visual identities into the textual space for precise grounding. To further enhance identity preservation and subject interaction,"},"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":"2506.07848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:11:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c32db7d53af7f89e00e2e68447327bf79d7d3e45e25676380de66eb99e9a7fe","abstract_canon_sha256":"c628a2d13f5cbfcb04cf38fffd41f81f7c150d1f67382ff29020837e308873f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:34.393497Z","signature_b64":"uqLrSGYpYbSlK2IfAFhrIHJkIQ6xw0cL3wOhHscjeGCbu42mmcMPHijLVJcZjrWQZ1d7OgvSposLgphceq5YBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74aebb26d616e3ffe0846147810fda89007093ba0d8b3f72949f2baa7840a260","last_reissued_at":"2026-07-05T11:18:34.392989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:34.392989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Qinglin Lu, Ran Yi, Teng Hu, Yuan Zhou, Zhengguang Zhou, Zhentao Yu","submitted_at":"2025-06-09T15:11:09Z","abstract_excerpt":"Despite recent advances in video generation, existing models still lack fine-grained controllability, especially for multi-subject customization with consistent identity and interaction. In this paper, we propose PolyVivid, a multi-subject video customization framework that enables flexible and identity-consistent generation. To establish accurate correspondences between subject images and textual entities, we design a VLLM-based text-image fusion module that embeds visual identities into the textual space for precise grounding. To further enhance identity preservation and subject interaction,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07848","kind":"arxiv","version":1},"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/2506.07848/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":"2506.07848","created_at":"2026-07-05T11:18:34.393049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07848v1","created_at":"2026-07-05T11:18:34.393049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07848","created_at":"2026-07-05T11:18:34.393049+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSXLWJWWC3R7","created_at":"2026-07-05T11:18:34.393049+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSXLWJWWC3R77YEE","created_at":"2026-07-05T11:18:34.393049+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSXLWJWW","created_at":"2026-07-05T11:18:34.393049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02753","citing_title":"MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11363","citing_title":"PresentAgent-2: Towards Generalist Multimodal Presentation Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":206,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE","json":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE.json","graph_json":"https://pith.science/api/pith-number/OSXLWJWWC3R77YEEMFDYCD62RE/graph.json","events_json":"https://pith.science/api/pith-number/OSXLWJWWC3R77YEEMFDYCD62RE/events.json","paper":"https://pith.science/paper/OSXLWJWW"},"agent_actions":{"view_html":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE","download_json":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE.json","view_paper":"https://pith.science/paper/OSXLWJWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07848&json=true","fetch_graph":"https://pith.science/api/pith-number/OSXLWJWWC3R77YEEMFDYCD62RE/graph.json","fetch_events":"https://pith.science/api/pith-number/OSXLWJWWC3R77YEEMFDYCD62RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE/action/storage_attestation","attest_author":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE/action/author_attestation","sign_citation":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE/action/citation_signature","submit_replication":"https://pith.science/pith/OSXLWJWWC3R77YEEMFDYCD62RE/action/replication_record"}},"created_at":"2026-07-05T11:18:34.393049+00:00","updated_at":"2026-07-05T11:18:34.393049+00:00"}