{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ELWP4NFRC4VGOABG2UOHTURCHW","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":"752d96efb96579967b1c34e124f1c31a40d8b112039d376a1ed85e7c65499919","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T12:12:45Z","title_canon_sha256":"9e8d376a8ff9c911028b0182d562ac84505bef7b0f2274ab7648f7bca1305d92"},"schema_version":"1.0","source":{"id":"2412.11694","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11694","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11694v3","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11694","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_12","alias_value":"ELWP4NFRC4VG","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_16","alias_value":"ELWP4NFRC4VGOABG","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_8","alias_value":"ELWP4NFR","created_at":"2026-07-05T10:23:27Z"}],"graph_snapshots":[{"event_id":"sha256:75cbb20bf6c4d7f0bbde795d8eb20e46df2abe6d9f86c809e557d8361b822d0c","target":"graph","created_at":"2026-07-05T10:23:27Z","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/2412.11694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To tackle complex tasks in real-world scenarios, more researchers are focusing on Omni-MLLMs, which aim to achieve omni-modal understanding and generation. Beyond the constraints of any specific non-linguistic modality, Omni-MLLMs map various non-linguistic modalities into the embedding space of LLMs and enable the interaction and understanding of arbitrary combinations of modalities within a single model. In this paper, we systematically investigate relevant research and provide a comprehensive survey of Omni-MLLMs. Specifically, we first explain the four core components of Omni-MLLMs for uni","authors_text":"Bing Qin, Heng Chang, Jiafeng Liang, Jinhua Du, Jiyuan Wang, Ming Liu, Shixin Jiang, Weijiang Yu, Xuan Dong","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T12:12:45Z","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11694","kind":"arxiv","version":3},"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:aa0cf3806c1c1b5594c3a468a55b26e1e2f7e48ae68776d4ec6dd0ba43bb9f1c","target":"record","created_at":"2026-07-05T10:23:27Z","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":"752d96efb96579967b1c34e124f1c31a40d8b112039d376a1ed85e7c65499919","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T12:12:45Z","title_canon_sha256":"9e8d376a8ff9c911028b0182d562ac84505bef7b0f2274ab7648f7bca1305d92"},"schema_version":"1.0","source":{"id":"2412.11694","kind":"arxiv","version":3}},"canonical_sha256":"22ecfe34b1172a670026d51c79d2223d9750c92657f4fddc4162920c76ef1a9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22ecfe34b1172a670026d51c79d2223d9750c92657f4fddc4162920c76ef1a9a","first_computed_at":"2026-07-05T10:23:27.635944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:27.635944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"scfIfUnZtmlzX1j6v2fAW+gkSd4gk6AgCrgMo9n+4ZpuJXe0DKRgnOCTYcT2FjRrUzD+VD0okSpe9ARzJqyKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:27.636438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11694","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa0cf3806c1c1b5594c3a468a55b26e1e2f7e48ae68776d4ec6dd0ba43bb9f1c","sha256:75cbb20bf6c4d7f0bbde795d8eb20e46df2abe6d9f86c809e557d8361b822d0c"],"state_sha256":"7b4e4461c5ed20927ae6ad318ba46c5310622c5961d68f766e7653f91cd59e04"}