{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KH6WYOATI6WE4DHPK2RHU3WX3V","short_pith_number":"pith:KH6WYOAT","canonical_record":{"source":{"id":"2405.19334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T17:59:20Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","cs.SD"],"title_canon_sha256":"ba586aef97032272c0f771be620d0997ad13c10d202697a09fbb3c39cb958941","abstract_canon_sha256":"6bfad9ce65f507d36c73890113b86bdba0204fcd49db461ed73a8d8822a2d22d"},"schema_version":"1.0"},"canonical_sha256":"51fd6c381347ac4e0cef56a27a6ed7dd586e4b46c9704a4f51dd7aec91de8ed4","source":{"kind":"arxiv","id":"2405.19334","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19334","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19334v2","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19334","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"KH6WYOATI6WE","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KH6WYOATI6WE4DHP","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KH6WYOAT","created_at":"2026-07-05T08:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KH6WYOATI6WE4DHPK2RHU3WX3V","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T17:59:20Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","cs.SD"],"title_canon_sha256":"ba586aef97032272c0f771be620d0997ad13c10d202697a09fbb3c39cb958941","abstract_canon_sha256":"6bfad9ce65f507d36c73890113b86bdba0204fcd49db461ed73a8d8822a2d22d"},"schema_version":"1.0"},"canonical_sha256":"51fd6c381347ac4e0cef56a27a6ed7dd586e4b46c9704a4f51dd7aec91de8ed4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:27.271572Z","signature_b64":"ssLY9/B5YWFcaniy5yZ4c4SDiD9U+CPvbOhbeOXltUMh2virzo4pcT81OVjOSQr7Zr96Q+r3wtVkI2Imoex9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51fd6c381347ac4e0cef56a27a6ed7dd586e4b46c9704a4f51dd7aec91de8ed4","last_reissued_at":"2026-07-05T08:29:27.270999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:27.270999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19334","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m36riCIbrNhrNUo5oo+PA7rNOqZKZIGKl/Q1bjjwf8NnhwcVqF9EvdKfsbHJ0g9HdbumGeo5dD+jKF4tVno4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:46:01.668623Z"},"content_sha256":"788b25beaef36e01742418abb19d24351633f15647ac32c5446c0624f65ef87c","schema_version":"1.0","event_id":"sha256:788b25beaef36e01742418abb19d24351633f15647ac32c5446c0624f65ef87c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KH6WYOATI6WE4DHPK2RHU3WX3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs Meet Multimodal Generation and Editing: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM","cs.SD"],"primary_cat":"cs.AI","authors_text":"Hongyu Liu, Jifeng Dai, Jingye Chen, Qifeng Chen, Qifeng Liu, Ruibin Yuan, Runtao Liu, Wei Xue, Wenhai Wang, Xiaowei Chi, Yazhou Xing, Yike Guo, Yingqing He, Yong Zhang, Zeyue Tian, Zhaoyang Liu","submitted_at":"2024-05-29T17:59:20Z","abstract_excerpt":"With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal understanding. This survey elaborates on multimodal generation and editing across various domains, comprising image, video, 3D, and audio. Specifically, we summarize the notable advancements with milestone works in these fields and categorize these studies into LLM-based and CLIP/T5-based methods. Then, we summarize the various roles of LLMs in multimodal generation and exhaus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19334","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/2405.19334/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cxswMgF9SUk479fx6BONuf0G0IoQF299OaQq1Wyh5Ldg/hW3NIxnD9pnKFl1x/7AmUnfl4vaI/VkCBAOWS1yCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:46:01.669499Z"},"content_sha256":"3a3eebf54cb65bfe5b07c940451d582331fc92bd018a2ff6a23bf0719482622a","schema_version":"1.0","event_id":"sha256:3a3eebf54cb65bfe5b07c940451d582331fc92bd018a2ff6a23bf0719482622a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KH6WYOATI6WE4DHPK2RHU3WX3V/bundle.json","state_url":"https://pith.science/pith/KH6WYOATI6WE4DHPK2RHU3WX3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KH6WYOATI6WE4DHPK2RHU3WX3V/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T07:46:01Z","links":{"resolver":"https://pith.science/pith/KH6WYOATI6WE4DHPK2RHU3WX3V","bundle":"https://pith.science/pith/KH6WYOATI6WE4DHPK2RHU3WX3V/bundle.json","state":"https://pith.science/pith/KH6WYOATI6WE4DHPK2RHU3WX3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KH6WYOATI6WE4DHPK2RHU3WX3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KH6WYOATI6WE4DHPK2RHU3WX3V","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6bfad9ce65f507d36c73890113b86bdba0204fcd49db461ed73a8d8822a2d22d","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T17:59:20Z","title_canon_sha256":"ba586aef97032272c0f771be620d0997ad13c10d202697a09fbb3c39cb958941"},"schema_version":"1.0","source":{"id":"2405.19334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19334","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19334v2","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19334","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"KH6WYOATI6WE","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KH6WYOATI6WE4DHP","created_at":"2026-07-05T08:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KH6WYOAT","created_at":"2026-07-05T08:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:3a3eebf54cb65bfe5b07c940451d582331fc92bd018a2ff6a23bf0719482622a","target":"graph","created_at":"2026-07-05T08:29:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.19334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal understanding. This survey elaborates on multimodal generation and editing across various domains, comprising image, video, 3D, and audio. Specifically, we summarize the notable advancements with milestone works in these fields and categorize these studies into LLM-based and CLIP/T5-based methods. Then, we summarize the various roles of LLMs in multimodal generation and exhaus","authors_text":"Hongyu Liu, Jifeng Dai, Jingye Chen, Qifeng Chen, Qifeng Liu, Ruibin Yuan, Runtao Liu, Wei Xue, Wenhai Wang, Xiaowei Chi, Yazhou Xing, Yike Guo, Yingqing He, Yong Zhang, Zeyue Tian, Zhaoyang Liu","cross_cats":["cs.CL","cs.CV","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T17:59:20Z","title":"LLMs Meet Multimodal Generation and Editing: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19334","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:788b25beaef36e01742418abb19d24351633f15647ac32c5446c0624f65ef87c","target":"record","created_at":"2026-07-05T08:29:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6bfad9ce65f507d36c73890113b86bdba0204fcd49db461ed73a8d8822a2d22d","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T17:59:20Z","title_canon_sha256":"ba586aef97032272c0f771be620d0997ad13c10d202697a09fbb3c39cb958941"},"schema_version":"1.0","source":{"id":"2405.19334","kind":"arxiv","version":2}},"canonical_sha256":"51fd6c381347ac4e0cef56a27a6ed7dd586e4b46c9704a4f51dd7aec91de8ed4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51fd6c381347ac4e0cef56a27a6ed7dd586e4b46c9704a4f51dd7aec91de8ed4","first_computed_at":"2026-07-05T08:29:27.270999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:27.270999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ssLY9/B5YWFcaniy5yZ4c4SDiD9U+CPvbOhbeOXltUMh2virzo4pcT81OVjOSQr7Zr96Q+r3wtVkI2Imoex9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:27.271572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:788b25beaef36e01742418abb19d24351633f15647ac32c5446c0624f65ef87c","sha256:3a3eebf54cb65bfe5b07c940451d582331fc92bd018a2ff6a23bf0719482622a"],"state_sha256":"5e3f3b3ee693ae5e98eef3804a0013217ddfc346d6403f07fbbd9dab570735f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s2elGuRQnoLYwOiQKN3GESzO8AUrFxtXrhqnMxlxNG5ZbPC47xeshvkkO7QXXT7oXmm2c0j8OUOLs5cImWXxDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:46:01.675137Z","bundle_sha256":"8cb05bb484d737d1e642686a575bc601341dc7c58f59c3c6b26ced1f15b4f8cd"}}