{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZPXUBAQJE4HJASYMJGC6TPJEX3","short_pith_number":"pith:ZPXUBAQJ","schema_version":"1.0","canonical_sha256":"cbef408209270e904b0c4985e9bd24bee14064ad22ecc67865e0b1ed92059571","source":{"kind":"arxiv","id":"2504.13162","version":1},"attestation_state":"computed","paper":{"title":"Personalized Text-to-Image Generation with Auto-Regressive Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyue Sun, Xian Liu, Xihui Liu, Yao Teng","submitted_at":"2025-04-17T17:58:26Z","abstract_excerpt":"Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain, auto-regressive models, with their unified architecture for text and image modeling, remain underexplored for personalized image generation. This paper investigates the potential of optimizing auto-regressive models for personalized image synthesis, leveraging their inherent multimodal capabilities to perform this task. We propose a two-stage training strategy that combi"},"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":"2504.13162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T17:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"54f2bfab17abdc69a3df87458ca22e10b97b5461c17cc2f79700234cef566e1e","abstract_canon_sha256":"d5af961c1b7e365c75aba6dc968863f8118e43cca006d2bac072460f3c1ad1a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:38.615220Z","signature_b64":"U57XfAtUTmJWjnL3F4ew2YEapq3Ji2waNrmbaZoz0u0qTMhc0F6PFt177qvJ4xuU9s0JnGivPhJMHxRtmrEPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbef408209270e904b0c4985e9bd24bee14064ad22ecc67865e0b1ed92059571","last_reissued_at":"2026-07-05T10:50:38.614724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:38.614724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Text-to-Image Generation with Auto-Regressive Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyue Sun, Xian Liu, Xihui Liu, Yao Teng","submitted_at":"2025-04-17T17:58:26Z","abstract_excerpt":"Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain, auto-regressive models, with their unified architecture for text and image modeling, remain underexplored for personalized image generation. This paper investigates the potential of optimizing auto-regressive models for personalized image synthesis, leveraging their inherent multimodal capabilities to perform this task. We propose a two-stage training strategy that combi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13162","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/2504.13162/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":"2504.13162","created_at":"2026-07-05T10:50:38.614784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13162v1","created_at":"2026-07-05T10:50:38.614784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13162","created_at":"2026-07-05T10:50:38.614784+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPXUBAQJE4HJ","created_at":"2026-07-05T10:50:38.614784+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPXUBAQJE4HJASYM","created_at":"2026-07-05T10:50:38.614784+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPXUBAQJ","created_at":"2026-07-05T10:50:38.614784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3","json":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3.json","graph_json":"https://pith.science/api/pith-number/ZPXUBAQJE4HJASYMJGC6TPJEX3/graph.json","events_json":"https://pith.science/api/pith-number/ZPXUBAQJE4HJASYMJGC6TPJEX3/events.json","paper":"https://pith.science/paper/ZPXUBAQJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3","download_json":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3.json","view_paper":"https://pith.science/paper/ZPXUBAQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13162&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPXUBAQJE4HJASYMJGC6TPJEX3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPXUBAQJE4HJASYMJGC6TPJEX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3/action/storage_attestation","attest_author":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3/action/author_attestation","sign_citation":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3/action/citation_signature","submit_replication":"https://pith.science/pith/ZPXUBAQJE4HJASYMJGC6TPJEX3/action/replication_record"}},"created_at":"2026-07-05T10:50:38.614784+00:00","updated_at":"2026-07-05T10:50:38.614784+00:00"}