{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NWNRCSYM3GYCDVXYPKI5CB6BG4","short_pith_number":"pith:NWNRCSYM","schema_version":"1.0","canonical_sha256":"6d9b114b0cd9b021d6f87a91d107c1373ec99630bbc551b6af688ca7274509b5","source":{"kind":"arxiv","id":"2312.07886","version":1},"attestation_state":"computed","paper":{"title":"Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Boyuan Yang, Kai Huang, Wei Gao","submitted_at":"2023-12-13T04:08:59Z","abstract_excerpt":"Large Language Models (LLMs) are capable of reasoning over diverse input data modalities through pre-trained encoders. However, the growing diversity of input data modalities prevents incorporating all modalities into LLMs, especially when LLMs are deployed on resource-constrained edge devices for embodied AI applications. Instead, a better option is to adaptively involve only the useful modalities at runtime, depending on the current environmental contexts and task requirements. For such modality adaptation, existing work adopts fixed connections between encoders and the LLM's input layer, le"},"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":"2312.07886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T04:08:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"da3571c8d7276dd84d2a81f2c4d54522bf3a5bea1dce868b05011b4d2a05c22b","abstract_canon_sha256":"bdfa8397afa5dec28d3439cb2bd254282d809ac2a6f167c0e7aaa163d1358e33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:38.737675Z","signature_b64":"kiy0Xm2KRoU8jsUgEsHkCzmXJiWEogjQ+O55AKWaPXh5QZMLysl2t5mW/UAYP6F8l1peuydbNQEMNGK0wERiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d9b114b0cd9b021d6f87a91d107c1373ec99630bbc551b6af688ca7274509b5","last_reissued_at":"2026-07-05T07:23:38.737116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:38.737116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Boyuan Yang, Kai Huang, Wei Gao","submitted_at":"2023-12-13T04:08:59Z","abstract_excerpt":"Large Language Models (LLMs) are capable of reasoning over diverse input data modalities through pre-trained encoders. However, the growing diversity of input data modalities prevents incorporating all modalities into LLMs, especially when LLMs are deployed on resource-constrained edge devices for embodied AI applications. Instead, a better option is to adaptively involve only the useful modalities at runtime, depending on the current environmental contexts and task requirements. For such modality adaptation, existing work adopts fixed connections between encoders and the LLM's input layer, le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07886","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/2312.07886/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":"2312.07886","created_at":"2026-07-05T07:23:38.737174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07886v1","created_at":"2026-07-05T07:23:38.737174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07886","created_at":"2026-07-05T07:23:38.737174+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWNRCSYM3GYC","created_at":"2026-07-05T07:23:38.737174+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWNRCSYM3GYCDVXY","created_at":"2026-07-05T07:23:38.737174+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWNRCSYM","created_at":"2026-07-05T07:23:38.737174+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/NWNRCSYM3GYCDVXYPKI5CB6BG4","json":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4.json","graph_json":"https://pith.science/api/pith-number/NWNRCSYM3GYCDVXYPKI5CB6BG4/graph.json","events_json":"https://pith.science/api/pith-number/NWNRCSYM3GYCDVXYPKI5CB6BG4/events.json","paper":"https://pith.science/paper/NWNRCSYM"},"agent_actions":{"view_html":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4","download_json":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4.json","view_paper":"https://pith.science/paper/NWNRCSYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07886&json=true","fetch_graph":"https://pith.science/api/pith-number/NWNRCSYM3GYCDVXYPKI5CB6BG4/graph.json","fetch_events":"https://pith.science/api/pith-number/NWNRCSYM3GYCDVXYPKI5CB6BG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4/action/storage_attestation","attest_author":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4/action/author_attestation","sign_citation":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4/action/citation_signature","submit_replication":"https://pith.science/pith/NWNRCSYM3GYCDVXYPKI5CB6BG4/action/replication_record"}},"created_at":"2026-07-05T07:23:38.737174+00:00","updated_at":"2026-07-05T07:23:38.737174+00:00"}