{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BQ47AUFPLD6GFMZXKZVZPYA3YX","short_pith_number":"pith:BQ47AUFP","schema_version":"1.0","canonical_sha256":"0c39f050af58fc62b337566b97e01bc5fe725121e0b529818b2e886ac9cc70d2","source":{"kind":"arxiv","id":"2506.14015","version":1},"attestation_state":"computed","paper":{"title":"Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akin Caliskan, Berkay Kicanaoglu, Hyeongwoo Kim, James Tompkin, Nick Yiwen Huang","submitted_at":"2025-06-16T21:26:45Z","abstract_excerpt":"We consider the problem of disentangling 3D from large vision-language models, which we show on generative 3D portraits. This allows free-form text control of appearance attributes like age, hair style, and glasses, and 3D geometry control of face expression and camera pose. In this setting, we assume we use a pre-trained large vision-language model (LVLM; CLIP) to generate from a smaller 2D dataset with no additional paired labels and with a pre-defined 3D morphable model (FLAME). First, we disentangle using canonicalization to a 2D reference frame from a deformable neural 3D triplane represe"},"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":"2506.14015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T21:26:45Z","cross_cats_sorted":[],"title_canon_sha256":"8ebe41835470de62df89950b9ff7c0c4a6138ffd8fa8506f71209e010cc94542","abstract_canon_sha256":"53b6890f4734049abcb0894d197610327065d66c5086b63b3af9a2f7bee6dc3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:47.424654Z","signature_b64":"8vSW0WFecsnDcZGkOfyYaZ76GTEzCCjKp+t60Y4Ixj8TpWTCeCoNHPMTCM2LboBuPiqm11ODe170ngly3KbjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c39f050af58fc62b337566b97e01bc5fe725121e0b529818b2e886ac9cc70d2","last_reissued_at":"2026-07-05T11:22:47.424148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:47.424148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akin Caliskan, Berkay Kicanaoglu, Hyeongwoo Kim, James Tompkin, Nick Yiwen Huang","submitted_at":"2025-06-16T21:26:45Z","abstract_excerpt":"We consider the problem of disentangling 3D from large vision-language models, which we show on generative 3D portraits. This allows free-form text control of appearance attributes like age, hair style, and glasses, and 3D geometry control of face expression and camera pose. In this setting, we assume we use a pre-trained large vision-language model (LVLM; CLIP) to generate from a smaller 2D dataset with no additional paired labels and with a pre-defined 3D morphable model (FLAME). First, we disentangle using canonicalization to a 2D reference frame from a deformable neural 3D triplane represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14015","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/2506.14015/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":"2506.14015","created_at":"2026-07-05T11:22:47.424205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14015v1","created_at":"2026-07-05T11:22:47.424205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14015","created_at":"2026-07-05T11:22:47.424205+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQ47AUFPLD6G","created_at":"2026-07-05T11:22:47.424205+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQ47AUFPLD6GFMZX","created_at":"2026-07-05T11:22:47.424205+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQ47AUFP","created_at":"2026-07-05T11:22:47.424205+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/BQ47AUFPLD6GFMZXKZVZPYA3YX","json":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX.json","graph_json":"https://pith.science/api/pith-number/BQ47AUFPLD6GFMZXKZVZPYA3YX/graph.json","events_json":"https://pith.science/api/pith-number/BQ47AUFPLD6GFMZXKZVZPYA3YX/events.json","paper":"https://pith.science/paper/BQ47AUFP"},"agent_actions":{"view_html":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX","download_json":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX.json","view_paper":"https://pith.science/paper/BQ47AUFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14015&json=true","fetch_graph":"https://pith.science/api/pith-number/BQ47AUFPLD6GFMZXKZVZPYA3YX/graph.json","fetch_events":"https://pith.science/api/pith-number/BQ47AUFPLD6GFMZXKZVZPYA3YX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX/action/storage_attestation","attest_author":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX/action/author_attestation","sign_citation":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX/action/citation_signature","submit_replication":"https://pith.science/pith/BQ47AUFPLD6GFMZXKZVZPYA3YX/action/replication_record"}},"created_at":"2026-07-05T11:22:47.424205+00:00","updated_at":"2026-07-05T11:22:47.424205+00:00"}