{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XAXGFHPDA2D4Q2XCGYCZ7YX4AL","short_pith_number":"pith:XAXGFHPD","schema_version":"1.0","canonical_sha256":"b82e629de30687c86ae236059fe2fc02df387b44c869268c8c1cb6fa25e6d758","source":{"kind":"arxiv","id":"2508.11433","version":2},"attestation_state":"computed","paper":{"title":"MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinyu Guo, Jiwei Wei, Kuncheng Li, Ning Xie, Qian Liang, Shiyuan He, Yujia Wu","submitted_at":"2025-08-15T12:20:27Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation. Specifically, we structure"},"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":"2508.11433","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T12:20:27Z","cross_cats_sorted":[],"title_canon_sha256":"b81a21710f1d826c247ef3d84e1eafda5fa683537fc93b962beab1a38f566b74","abstract_canon_sha256":"0fbd5dd573860320026273874ff4c4e3cac61af4ee052fb44d499a1ee3264c72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:19.900090Z","signature_b64":"3v1gU3T6uDtwiEoRTDQdTX8zrKqCcHXnDJ5X9vnEP9KyQCXY5diUwVXsi9AjpizSs0ywMbwW2frvZahIaOjzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b82e629de30687c86ae236059fe2fc02df387b44c869268c8c1cb6fa25e6d758","last_reissued_at":"2026-07-05T11:59:19.899721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:19.899721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinyu Guo, Jiwei Wei, Kuncheng Li, Ning Xie, Qian Liang, Shiyuan He, Yujia Wu","submitted_at":"2025-08-15T12:20:27Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation. Specifically, we structure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11433","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/2508.11433/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":"2508.11433","created_at":"2026-07-05T11:59:19.899778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11433v2","created_at":"2026-07-05T11:59:19.899778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11433","created_at":"2026-07-05T11:59:19.899778+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAXGFHPDA2D4","created_at":"2026-07-05T11:59:19.899778+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAXGFHPDA2D4Q2XC","created_at":"2026-07-05T11:59:19.899778+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAXGFHPD","created_at":"2026-07-05T11:59:19.899778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26930","citing_title":"PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04442","citing_title":"Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10445","citing_title":"Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL","json":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL.json","graph_json":"https://pith.science/api/pith-number/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/graph.json","events_json":"https://pith.science/api/pith-number/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/events.json","paper":"https://pith.science/paper/XAXGFHPD"},"agent_actions":{"view_html":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL","download_json":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL.json","view_paper":"https://pith.science/paper/XAXGFHPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11433&json=true","fetch_graph":"https://pith.science/api/pith-number/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/graph.json","fetch_events":"https://pith.science/api/pith-number/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/action/storage_attestation","attest_author":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/action/author_attestation","sign_citation":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/action/citation_signature","submit_replication":"https://pith.science/pith/XAXGFHPDA2D4Q2XCGYCZ7YX4AL/action/replication_record"}},"created_at":"2026-07-05T11:59:19.899778+00:00","updated_at":"2026-07-05T11:59:19.899778+00:00"}