{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W6UTP3MY2EF4F5A2MDGRE3HNSD","short_pith_number":"pith:W6UTP3MY","schema_version":"1.0","canonical_sha256":"b7a937ed98d10bc2f41a60cd126ced90c2a71c3ddb779dbe1dbfb8eadd2a5798","source":{"kind":"arxiv","id":"2507.09574","version":3},"attestation_state":"computed","paper":{"title":"MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haozhe Zhao, Jiuxiang Gu, Junjie Hu, Liang Chen, Minjia Zhang, Shuzheng Si, Wen Xiao, Zefan Cai","submitted_at":"2025-07-13T10:52:59Z","abstract_excerpt":"Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we propose MENTOR, a novel autoregressive (AR) framework for efficient Multimodal-conditioned Tuning for Autoregressive multimodal image generation. MENTOR combines an AR image generator with a two-stage training paradigm, enabling fine-grained, token-level alignment between multimodal inputs and image outputs without relying on auxiliary adapters or cross-att"},"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":"2507.09574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T10:52:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a294a84ace8e87f345538817f879c41fe2f45ef8d21025d337ecd5928d5344c1","abstract_canon_sha256":"cbe066a2e41a00486c8b5fdb73aa1aa4bce5662ae6eb523cdc8644391fc3c1d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:54.401486Z","signature_b64":"BHpyYre+TaIIn3M8HN/UXCUgFCm7cB4bBP5Qt0meJCn+K1bldt0FFQ6tq55izG4pVas5Z2/boCg4yKgwK/ftAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7a937ed98d10bc2f41a60cd126ced90c2a71c3ddb779dbe1dbfb8eadd2a5798","last_reissued_at":"2026-05-29T01:04:54.399747Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:54.399747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haozhe Zhao, Jiuxiang Gu, Junjie Hu, Liang Chen, Minjia Zhang, Shuzheng Si, Wen Xiao, Zefan Cai","submitted_at":"2025-07-13T10:52:59Z","abstract_excerpt":"Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we propose MENTOR, a novel autoregressive (AR) framework for efficient Multimodal-conditioned Tuning for Autoregressive multimodal image generation. MENTOR combines an AR image generator with a two-stage training paradigm, enabling fine-grained, token-level alignment between multimodal inputs and image outputs without relying on auxiliary adapters or cross-att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09574","kind":"arxiv","version":3},"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/2507.09574/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":"2507.09574","created_at":"2026-05-29T01:04:54.399828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09574v3","created_at":"2026-05-29T01:04:54.399828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09574","created_at":"2026-05-29T01:04:54.399828+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6UTP3MY2EF4","created_at":"2026-05-29T01:04:54.399828+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6UTP3MY2EF4F5A2","created_at":"2026-05-29T01:04:54.399828+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6UTP3MY","created_at":"2026-05-29T01:04:54.399828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17291","citing_title":"Step-wise Rubric Rewards for LLM Reasoning","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD","json":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD.json","graph_json":"https://pith.science/api/pith-number/W6UTP3MY2EF4F5A2MDGRE3HNSD/graph.json","events_json":"https://pith.science/api/pith-number/W6UTP3MY2EF4F5A2MDGRE3HNSD/events.json","paper":"https://pith.science/paper/W6UTP3MY"},"agent_actions":{"view_html":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD","download_json":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD.json","view_paper":"https://pith.science/paper/W6UTP3MY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09574&json=true","fetch_graph":"https://pith.science/api/pith-number/W6UTP3MY2EF4F5A2MDGRE3HNSD/graph.json","fetch_events":"https://pith.science/api/pith-number/W6UTP3MY2EF4F5A2MDGRE3HNSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/action/storage_attestation","attest_author":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/action/author_attestation","sign_citation":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/action/citation_signature","submit_replication":"https://pith.science/pith/W6UTP3MY2EF4F5A2MDGRE3HNSD/action/replication_record"}},"created_at":"2026-05-29T01:04:54.399828+00:00","updated_at":"2026-05-29T01:04:54.399828+00:00"}