{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I74D4BZIHWBSHHPWGPI435XZSG","short_pith_number":"pith:I74D4BZI","schema_version":"1.0","canonical_sha256":"47f83e07283d83239df633d1cdf6f991a057f8bf0e3375a08cfa228b25e694cd","source":{"kind":"arxiv","id":"2501.06187","version":2},"attestation_state":"computed","paper":{"title":"Multi-subject Open-set Personalization in Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Ivan Skorokhodov, Jun-Yan Zhu, Kfir Aberman, Kwot Sin Lee, Ming-Hsuan Yang, Sergey Tulyakov, Tsai-Shien Chen, Willi Menapace, Yuwei Fang","submitted_at":"2025-01-10T18:59:54Z","abstract_excerpt":"Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only a single subject. We present Video Alchemist $-$ a video model with built-in multi-subject, open-set personalization capabilities for both foreground objects and background, eliminating the need for time-consuming test-time optimization. Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding"},"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":"2501.06187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T18:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"737de924cf720ba23a9192068786ef4a8aadda8a8787479338cef407381a37f0","abstract_canon_sha256":"401ad88093c730cb8bb4657cb19eb066d2676dc8d061117712ab22183f7c19d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:15.474339Z","signature_b64":"1vDJpBl0mN3c5KSHc5tZQE7xe0L2NX3Zl08vr51QBbi1/sbiJPmWvmf4bAJBSQyZcutgG16+nHBBQq5dOHxiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f83e07283d83239df633d1cdf6f991a057f8bf0e3375a08cfa228b25e694cd","last_reissued_at":"2026-07-05T10:36:15.473708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:15.473708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-subject Open-set Personalization in Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Ivan Skorokhodov, Jun-Yan Zhu, Kfir Aberman, Kwot Sin Lee, Ming-Hsuan Yang, Sergey Tulyakov, Tsai-Shien Chen, Willi Menapace, Yuwei Fang","submitted_at":"2025-01-10T18:59:54Z","abstract_excerpt":"Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only a single subject. We present Video Alchemist $-$ a video model with built-in multi-subject, open-set personalization capabilities for both foreground objects and background, eliminating the need for time-consuming test-time optimization. Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06187","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/2501.06187/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":"2501.06187","created_at":"2026-07-05T10:36:15.473788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06187v2","created_at":"2026-07-05T10:36:15.473788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06187","created_at":"2026-07-05T10:36:15.473788+00:00"},{"alias_kind":"pith_short_12","alias_value":"I74D4BZIHWBS","created_at":"2026-07-05T10:36:15.473788+00:00"},{"alias_kind":"pith_short_16","alias_value":"I74D4BZIHWBSHHPW","created_at":"2026-07-05T10:36:15.473788+00:00"},{"alias_kind":"pith_short_8","alias_value":"I74D4BZI","created_at":"2026-07-05T10:36:15.473788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.17816","citing_title":"Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":201,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG","json":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG.json","graph_json":"https://pith.science/api/pith-number/I74D4BZIHWBSHHPWGPI435XZSG/graph.json","events_json":"https://pith.science/api/pith-number/I74D4BZIHWBSHHPWGPI435XZSG/events.json","paper":"https://pith.science/paper/I74D4BZI"},"agent_actions":{"view_html":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG","download_json":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG.json","view_paper":"https://pith.science/paper/I74D4BZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06187&json=true","fetch_graph":"https://pith.science/api/pith-number/I74D4BZIHWBSHHPWGPI435XZSG/graph.json","fetch_events":"https://pith.science/api/pith-number/I74D4BZIHWBSHHPWGPI435XZSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG/action/storage_attestation","attest_author":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG/action/author_attestation","sign_citation":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG/action/citation_signature","submit_replication":"https://pith.science/pith/I74D4BZIHWBSHHPWGPI435XZSG/action/replication_record"}},"created_at":"2026-07-05T10:36:15.473788+00:00","updated_at":"2026-07-05T10:36:15.473788+00:00"}