{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PAAQFJO2ZD7BKQOQ3TSFRUDYJX","short_pith_number":"pith:PAAQFJO2","schema_version":"1.0","canonical_sha256":"780102a5dac8fe1541d0dce458d0784defd4fa6b632b80271ce3a198e675ee8b","source":{"kind":"arxiv","id":"2507.17801","version":1},"attestation_state":"computed","paper":{"title":"Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Dongyang Liu, Guangtao Zhai, Hongsheng Li, Juncheng Yan, Le Zhuo, Mengmeng Wang, Peng Gao, Qi Qin, Renrui Zhang, Shicheng Li, Siqi Luo, Tiancheng Han, Victor Shea-Jay Huang, Xiaohong Liu, Xiaoqing Sun, Yi Xin, Yuewen Cao, Yupeng Zhou, Yu Qiao, Zhen Li","submitted_at":"2025-07-23T17:42:13Z","abstract_excerpt":"We present Lumina-mGPT 2.0, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond. Unlike existing approaches that rely on pretrained components or hybrid architectures, Lumina-mGPT 2.0 is trained entirely from scratch, enabling unrestricted architectural design and licensing freedom. It achieves generation quality on par with state-of-the-art diffusion models such as DALL-E 3 and SANA, while preserving the inherent flexibility and compositionality of autoregressive modeling. Our unified tokenizat"},"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":"2507.17801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-23T17:42:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a924cf7df5aaceac03efc5e53555ad0780e0f6f9f514993ae54c55993d28d8a","abstract_canon_sha256":"a020834c64cf87be66864e2574d8e639050c17688de0ece23ddf2076769bb94c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:35.548402Z","signature_b64":"jvzol1rhL3CNXzn++h0/MB0RiDK/rGcobliiCB8jNQxweXb/YOx2wrOLXbxM4T9XomVw5MV8fH+CHLMB1F4kCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"780102a5dac8fe1541d0dce458d0784defd4fa6b632b80271ce3a198e675ee8b","last_reissued_at":"2026-07-05T11:42:35.547896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:35.547896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Dongyang Liu, Guangtao Zhai, Hongsheng Li, Juncheng Yan, Le Zhuo, Mengmeng Wang, Peng Gao, Qi Qin, Renrui Zhang, Shicheng Li, Siqi Luo, Tiancheng Han, Victor Shea-Jay Huang, Xiaohong Liu, Xiaoqing Sun, Yi Xin, Yuewen Cao, Yupeng Zhou, Yu Qiao, Zhen Li","submitted_at":"2025-07-23T17:42:13Z","abstract_excerpt":"We present Lumina-mGPT 2.0, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond. Unlike existing approaches that rely on pretrained components or hybrid architectures, Lumina-mGPT 2.0 is trained entirely from scratch, enabling unrestricted architectural design and licensing freedom. It achieves generation quality on par with state-of-the-art diffusion models such as DALL-E 3 and SANA, while preserving the inherent flexibility and compositionality of autoregressive modeling. Our unified tokenizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17801","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/2507.17801/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":"2507.17801","created_at":"2026-07-05T11:42:35.547959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17801v1","created_at":"2026-07-05T11:42:35.547959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17801","created_at":"2026-07-05T11:42:35.547959+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAAQFJO2ZD7B","created_at":"2026-07-05T11:42:35.547959+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAAQFJO2ZD7BKQOQ","created_at":"2026-07-05T11:42:35.547959+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAAQFJO2","created_at":"2026-07-05T11:42:35.547959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05703","citing_title":"Parallel Jacobi Decoding for Fast Autoregressive Image Generation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28938","citing_title":"EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16842","citing_title":"Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13587","citing_title":"VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19433","citing_title":"dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14333","citing_title":"InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12138","citing_title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09430","citing_title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09430","citing_title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20539","citing_title":"Animator-Centric Skeleton Generation on Objects with Fine-Grained Details","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX","json":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX.json","graph_json":"https://pith.science/api/pith-number/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/graph.json","events_json":"https://pith.science/api/pith-number/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/events.json","paper":"https://pith.science/paper/PAAQFJO2"},"agent_actions":{"view_html":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX","download_json":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX.json","view_paper":"https://pith.science/paper/PAAQFJO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17801&json=true","fetch_graph":"https://pith.science/api/pith-number/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/graph.json","fetch_events":"https://pith.science/api/pith-number/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/action/storage_attestation","attest_author":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/action/author_attestation","sign_citation":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/action/citation_signature","submit_replication":"https://pith.science/pith/PAAQFJO2ZD7BKQOQ3TSFRUDYJX/action/replication_record"}},"created_at":"2026-07-05T11:42:35.547959+00:00","updated_at":"2026-07-05T11:42:35.547959+00:00"}