{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NOE5TNB5M3JEXV2H2SFPTBCYBU","short_pith_number":"pith:NOE5TNB5","schema_version":"1.0","canonical_sha256":"6b89d9b43d66d24bd747d48af984580d2c2450ff9b113ef15376397d8b9489be","source":{"kind":"arxiv","id":"2505.05472","version":2},"attestation_state":"computed","paper":{"title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Mogao is a single model that generates arbitrary sequences mixing text and images by fusing autoregressive and diffusion components.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Liao, Jie Wu, Liang Li, Liyang Liu, Weilin Huang, Wenliang Zhao, Xinyu Zhang, Xun Wang, Zhengxiong Luo, Zhi Tian","submitted_at":"2025-05-08T17:58:57Z","abstract_excerpt":"Recent progress in unified models for image understanding and generation has been impressive, yet most approaches remain limited to single-modal generation conditioned on multiple modalities. In this paper, we present Mogao, a unified framework that advances this paradigm by enabling interleaved multi-modal generation through a causal approach. Mogao integrates a set of key technical improvements in architecture design, including a deep-fusion design, dual vision encoders, interleaved rotary position embeddings, and multi-modal classifier-free guidance, which allow it to harness the strengths "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2505.05472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T17:58:57Z","cross_cats_sorted":[],"title_canon_sha256":"2901d2f3db0f233e2de4c877ae6dbb6888068a827bb4c6b701deff4db654f564","abstract_canon_sha256":"37ebe6436300552155727322e1e80dae910b976364d4b35c782a49b466a7c6a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.724379Z","signature_b64":"wYht+DcF7TL3muhtTq8LiZwhCt3OG0ublijDJ8XtZYV8b8/ZU6bAc8qAD4UA/F0PRojosopJp9+UAVgsebOfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b89d9b43d66d24bd747d48af984580d2c2450ff9b113ef15376397d8b9489be","last_reissued_at":"2026-05-17T23:38:14.723810Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.723810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Mogao is a single model that generates arbitrary sequences mixing text and images by fusing autoregressive and diffusion components.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Liao, Jie Wu, Liang Li, Liyang Liu, Weilin Huang, Wenliang Zhao, Xinyu Zhang, Xun Wang, Zhengxiong Luo, Zhi Tian","submitted_at":"2025-05-08T17:58:57Z","abstract_excerpt":"Recent progress in unified models for image understanding and generation has been impressive, yet most approaches remain limited to single-modal generation conditioned on multiple modalities. In this paper, we present Mogao, a unified framework that advances this paradigm by enabling interleaved multi-modal generation through a causal approach. Mogao integrates a set of key technical improvements in architecture design, including a deep-fusion design, dual vision encoders, interleaved rotary position embeddings, and multi-modal classifier-free guidance, which allow it to harness the strengths "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Mogao not only achieves state-of-the-art performance in multi-modal understanding and text-to-image generation, but also excels in producing high-quality, coherent interleaved outputs. Its emergent capabilities in zero-shot image editing and compositional generation highlight Mogao as a practical omni-modal foundation model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The key technical improvements (deep-fusion design, dual vision encoders, interleaved rotary position embeddings, and multi-modal classifier-free guidance) successfully combine the strengths of autoregressive text models and diffusion image models for arbitrary interleaved sequences.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mogao is a single model that generates arbitrary sequences mixing text and images by fusing autoregressive and diffusion components.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bf1f45e253a85302aa1d5040e96a7df07fd3449de3d7b21a854d1d16a302836a"},"source":{"id":"2505.05472","kind":"arxiv","version":2},"verdict":{"id":"e4dc66b9-5e09-4357-a230-27a0a06abfe0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T07:18:40.194337Z","strongest_claim":"Mogao not only achieves state-of-the-art performance in multi-modal understanding and text-to-image generation, but also excels in producing high-quality, coherent interleaved outputs. Its emergent capabilities in zero-shot image editing and compositional generation highlight Mogao as a practical omni-modal foundation model.","one_line_summary":"Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The key technical improvements (deep-fusion design, dual vision encoders, interleaved rotary position embeddings, and multi-modal classifier-free guidance) successfully combine the strengths of autoregressive text models and diffusion image models for arbitrary interleaved sequences.","pith_extraction_headline":"Mogao is a single model that generates arbitrary sequences mixing text and images by fusing autoregressive and diffusion components."},"references":{"count":99,"sample":[{"doi":"","year":2024,"title":"Pixtral 12b.arXiv preprint arXiv:2410.07073, 2024","work_id":"9ad2b071-82d8-4cfa-b994-b9975094b575","ref_index":1,"cited_arxiv_id":"2410.07073","is_internal_anchor":true},{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning","work_id":"b61d581d-a5f8-4799-a638-d91ddfc06da4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":3,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":4,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":2023,"title":"Improving image generation with better captions.Computer Science","work_id":"fb7509a6-ece6-4ea3-b583-1ec884016dc8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":99,"snapshot_sha256":"08c6054537d19ec7e98dafbb8ea80acc44e066f2b817c034c113ca16062ba8d0","internal_anchors":37},"formal_canon":{"evidence_count":3,"snapshot_sha256":"b7903a9725fa117ff04df9c21506486f30477dfc034a2c0d69cced73bf9617af"},"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":"2505.05472","created_at":"2026-05-17T23:38:14.723899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05472v2","created_at":"2026-05-17T23:38:14.723899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05472","created_at":"2026-05-17T23:38:14.723899+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOE5TNB5M3JE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOE5TNB5M3JEXV2H","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOE5TNB5","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"2605.16961","citing_title":"Latent Action Control for Reasoning-Guided Unified Image Generation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2506.18871","citing_title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2511.19365","citing_title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2602.02493","citing_title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2602.12370","citing_title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2509.23951","citing_title":"HunyuanImage 3.0 Technical Report","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12305","citing_title":"Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12500","citing_title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08962","citing_title":"MegaScale-Omni: A Hyper-Scale, Workload-Resilient System for MultiModal LLM Training in Production","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05781","citing_title":"Steering Visual Generation in Unified Multimodal Models with Understanding Supervision","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08719","citing_title":"LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08029","citing_title":"STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":150,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14148","citing_title":"Seedance 2.0: Advancing Video Generation for World Complexity","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21904","citing_title":"UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02641","citing_title":"Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU","json":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU.json","graph_json":"https://pith.science/api/pith-number/NOE5TNB5M3JEXV2H2SFPTBCYBU/graph.json","events_json":"https://pith.science/api/pith-number/NOE5TNB5M3JEXV2H2SFPTBCYBU/events.json","paper":"https://pith.science/paper/NOE5TNB5"},"agent_actions":{"view_html":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU","download_json":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU.json","view_paper":"https://pith.science/paper/NOE5TNB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05472&json=true","fetch_graph":"https://pith.science/api/pith-number/NOE5TNB5M3JEXV2H2SFPTBCYBU/graph.json","fetch_events":"https://pith.science/api/pith-number/NOE5TNB5M3JEXV2H2SFPTBCYBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU/action/storage_attestation","attest_author":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU/action/author_attestation","sign_citation":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU/action/citation_signature","submit_replication":"https://pith.science/pith/NOE5TNB5M3JEXV2H2SFPTBCYBU/action/replication_record"}},"created_at":"2026-05-17T23:38:14.723899+00:00","updated_at":"2026-05-17T23:38:14.723899+00:00"}