{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QOTNTPGBL5E4PCJBXW2YPU7R3M","short_pith_number":"pith:QOTNTPGB","canonical_record":{"source":{"id":"2401.13601","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T17:10:45Z","cross_cats_sorted":[],"title_canon_sha256":"9069f74574bcea9714395059a1363bade539efa775d8949da8189db49f5310ff","abstract_canon_sha256":"17825c3ece254cfad8ce8d8be810dc02a11a2f9c9ffed23eaf9e99bf1c538070"},"schema_version":"1.0"},"canonical_sha256":"83a6d9bcc15f49c78921bdb587d3f1db14a80002bae616a1ea57ff9263cf3cda","source":{"kind":"arxiv","id":"2401.13601","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13601","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13601v5","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13601","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_12","alias_value":"QOTNTPGBL5E4","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_16","alias_value":"QOTNTPGBL5E4PCJB","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_8","alias_value":"QOTNTPGB","created_at":"2026-07-05T08:24:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QOTNTPGBL5E4PCJBXW2YPU7R3M","target":"record","payload":{"canonical_record":{"source":{"id":"2401.13601","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T17:10:45Z","cross_cats_sorted":[],"title_canon_sha256":"9069f74574bcea9714395059a1363bade539efa775d8949da8189db49f5310ff","abstract_canon_sha256":"17825c3ece254cfad8ce8d8be810dc02a11a2f9c9ffed23eaf9e99bf1c538070"},"schema_version":"1.0"},"canonical_sha256":"83a6d9bcc15f49c78921bdb587d3f1db14a80002bae616a1ea57ff9263cf3cda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:00.053304Z","signature_b64":"9Vlhi8oxWTlaYYCuyrdsX879pfkZH6UGxZ7sN59DXzDLxHyBktb7jBH6NrIitem3nvocj6CaxndtTlh/vsszCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83a6d9bcc15f49c78921bdb587d3f1db14a80002bae616a1ea57ff9263cf3cda","last_reissued_at":"2026-07-05T08:24:00.052826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:00.052826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.13601","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:24:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yf2mJTLKNfY1Emn1i1br0DTJZ02sA2UeiIuZmPM63SsfkVeTfR35nOPz1crVHOGaP5JreBiLYNcZWsybHzcICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:03:22.237756Z"},"content_sha256":"8ad3c81d32544c16e615e980a787e558758410e06ca0f8d65775d15b7d4f4edf","schema_version":"1.0","event_id":"sha256:8ad3c81d32544c16e615e980a787e558758410e06ca0f8d65775d15b7d4f4edf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QOTNTPGBL5E4PCJBXW2YPU7R3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenhui Chu, Chenxing Li, Dan Su, Dong Yu, Duzhen Zhang, Jiahua Dong, Yahan Yu","submitted_at":"2024-01-24T17:10:45Z","abstract_excerpt":"In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training strategies. The resulting models not only preserve the inherent reasoning and decision-making capabilities of LLMs but also empower a diverse range of MM tasks. In this paper, we provide a comprehensive survey aimed at facilitating further research of MM-LLMs. Initially, we outline general design formulations for model architecture and training pipeline. Subsequently, we introduce a taxonomy encompassing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13601","kind":"arxiv","version":5},"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/2401.13601/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":"2026-07-05T08:24:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WopBlu6TpgaQ/ebwBEMKTgMPr9Z6A0RzlChSw4eWkNUoyP08BbiX5TQsteBtAW//b7FcoBzCm+/cyZtKNx4wCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:03:22.238123Z"},"content_sha256":"d195145a063b652523f10505dc52974459a23c47f6254533c2963925395058d7","schema_version":"1.0","event_id":"sha256:d195145a063b652523f10505dc52974459a23c47f6254533c2963925395058d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QOTNTPGBL5E4PCJBXW2YPU7R3M/bundle.json","state_url":"https://pith.science/pith/QOTNTPGBL5E4PCJBXW2YPU7R3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QOTNTPGBL5E4PCJBXW2YPU7R3M/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":"2026-07-07T10:03:22Z","links":{"resolver":"https://pith.science/pith/QOTNTPGBL5E4PCJBXW2YPU7R3M","bundle":"https://pith.science/pith/QOTNTPGBL5E4PCJBXW2YPU7R3M/bundle.json","state":"https://pith.science/pith/QOTNTPGBL5E4PCJBXW2YPU7R3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QOTNTPGBL5E4PCJBXW2YPU7R3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QOTNTPGBL5E4PCJBXW2YPU7R3M","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":"17825c3ece254cfad8ce8d8be810dc02a11a2f9c9ffed23eaf9e99bf1c538070","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T17:10:45Z","title_canon_sha256":"9069f74574bcea9714395059a1363bade539efa775d8949da8189db49f5310ff"},"schema_version":"1.0","source":{"id":"2401.13601","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13601","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13601v5","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13601","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_12","alias_value":"QOTNTPGBL5E4","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_16","alias_value":"QOTNTPGBL5E4PCJB","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_8","alias_value":"QOTNTPGB","created_at":"2026-07-05T08:24:00Z"}],"graph_snapshots":[{"event_id":"sha256:d195145a063b652523f10505dc52974459a23c47f6254533c2963925395058d7","target":"graph","created_at":"2026-07-05T08:24:00Z","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/2401.13601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training strategies. The resulting models not only preserve the inherent reasoning and decision-making capabilities of LLMs but also empower a diverse range of MM tasks. In this paper, we provide a comprehensive survey aimed at facilitating further research of MM-LLMs. Initially, we outline general design formulations for model architecture and training pipeline. Subsequently, we introduce a taxonomy encompassing ","authors_text":"Chenhui Chu, Chenxing Li, Dan Su, Dong Yu, Duzhen Zhang, Jiahua Dong, Yahan Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T17:10:45Z","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13601","kind":"arxiv","version":5},"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":"sha256:8ad3c81d32544c16e615e980a787e558758410e06ca0f8d65775d15b7d4f4edf","target":"record","created_at":"2026-07-05T08:24:00Z","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":"17825c3ece254cfad8ce8d8be810dc02a11a2f9c9ffed23eaf9e99bf1c538070","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T17:10:45Z","title_canon_sha256":"9069f74574bcea9714395059a1363bade539efa775d8949da8189db49f5310ff"},"schema_version":"1.0","source":{"id":"2401.13601","kind":"arxiv","version":5}},"canonical_sha256":"83a6d9bcc15f49c78921bdb587d3f1db14a80002bae616a1ea57ff9263cf3cda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83a6d9bcc15f49c78921bdb587d3f1db14a80002bae616a1ea57ff9263cf3cda","first_computed_at":"2026-07-05T08:24:00.052826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:00.052826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Vlhi8oxWTlaYYCuyrdsX879pfkZH6UGxZ7sN59DXzDLxHyBktb7jBH6NrIitem3nvocj6CaxndtTlh/vsszCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:00.053304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13601","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ad3c81d32544c16e615e980a787e558758410e06ca0f8d65775d15b7d4f4edf","sha256:d195145a063b652523f10505dc52974459a23c47f6254533c2963925395058d7"],"state_sha256":"e4868203bfe2afd5391f6e3eaec5edb9e0649dbb41aaf921a37bea25a462f223"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDEnGDzWXmckZqUpIGslW5gmRtMXvPpBUvxGxc16OWoPAMf3oow4XFYEvP1V/D2WyOWRt1jaeH/nfjKOfceyAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:03:22.240711Z","bundle_sha256":"6f1738535ee22f5351345b2f23c2c86f7fbb6fe068feeeef024da94eb279d0f5"}}