{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B6FCSUC3WXMR6DD4IQB3TI26VK","short_pith_number":"pith:B6FCSUC3","schema_version":"1.0","canonical_sha256":"0f8a29505bb5d91f0c7c4403b9a35eaa8f95e1dd41e8b856f4b8677d556b801d","source":{"kind":"arxiv","id":"2606.29013","version":1},"attestation_state":"computed","paper":{"title":"Mural: Transferring LLM knowledge to image generation via Mixture-of-Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achin Jain, Davide Modolo, Jie An, Siddharth Chaudhary","submitted_at":"2026-06-27T17:18:07Z","abstract_excerpt":"Leveraging capabilities of large language models (LLMs) in text-to-image (T2I) synthesis is an important research direction. In this work we investigate whether the knowledge of a frozen LLM can be effectively utilized in T2I generation when trained exclusively on standard text-image pairs. We integrate a frozen, reasoning-capable LLM with a diffusion-based image generator via shared attention within the Mixture-of-Transformers (MoT) architecture. Our experiments span two critical questions: (1) what degree of the LLM's intrinsic knowledge remains accessible during T2I training, and (2) what n"},"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":"2606.29013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-27T17:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"808d5451a391def23f37ad5bbf8a1edf7a8d4342f95968f204b1b05fbb47c690","abstract_canon_sha256":"4f98e39c74349e806e6a3d47842d297dbe2e505520471cd0659a7f3965725392"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:49.464345Z","signature_b64":"NeCo3zwSl9LaeNCmJgkS8hZoUoHkKmrdtw8ERTMmGVUSnvCt4niBGqDgo00WIStvgALp+OWIF8/QA68Wb5l3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f8a29505bb5d91f0c7c4403b9a35eaa8f95e1dd41e8b856f4b8677d556b801d","last_reissued_at":"2026-06-30T01:17:49.463855Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:49.463855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mural: Transferring LLM knowledge to image generation via Mixture-of-Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achin Jain, Davide Modolo, Jie An, Siddharth Chaudhary","submitted_at":"2026-06-27T17:18:07Z","abstract_excerpt":"Leveraging capabilities of large language models (LLMs) in text-to-image (T2I) synthesis is an important research direction. In this work we investigate whether the knowledge of a frozen LLM can be effectively utilized in T2I generation when trained exclusively on standard text-image pairs. We integrate a frozen, reasoning-capable LLM with a diffusion-based image generator via shared attention within the Mixture-of-Transformers (MoT) architecture. Our experiments span two critical questions: (1) what degree of the LLM's intrinsic knowledge remains accessible during T2I training, and (2) what n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29013","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/2606.29013/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":"2606.29013","created_at":"2026-06-30T01:17:49.463923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29013v1","created_at":"2026-06-30T01:17:49.463923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29013","created_at":"2026-06-30T01:17:49.463923+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6FCSUC3WXMR","created_at":"2026-06-30T01:17:49.463923+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6FCSUC3WXMR6DD4","created_at":"2026-06-30T01:17:49.463923+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6FCSUC3","created_at":"2026-06-30T01:17:49.463923+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/B6FCSUC3WXMR6DD4IQB3TI26VK","json":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK.json","graph_json":"https://pith.science/api/pith-number/B6FCSUC3WXMR6DD4IQB3TI26VK/graph.json","events_json":"https://pith.science/api/pith-number/B6FCSUC3WXMR6DD4IQB3TI26VK/events.json","paper":"https://pith.science/paper/B6FCSUC3"},"agent_actions":{"view_html":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK","download_json":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK.json","view_paper":"https://pith.science/paper/B6FCSUC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29013&json=true","fetch_graph":"https://pith.science/api/pith-number/B6FCSUC3WXMR6DD4IQB3TI26VK/graph.json","fetch_events":"https://pith.science/api/pith-number/B6FCSUC3WXMR6DD4IQB3TI26VK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK/action/storage_attestation","attest_author":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK/action/author_attestation","sign_citation":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK/action/citation_signature","submit_replication":"https://pith.science/pith/B6FCSUC3WXMR6DD4IQB3TI26VK/action/replication_record"}},"created_at":"2026-06-30T01:17:49.463923+00:00","updated_at":"2026-06-30T01:17:49.463923+00:00"}