{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LIU5MCT5XOXMZIPHXYEST22UYZ","short_pith_number":"pith:LIU5MCT5","schema_version":"1.0","canonical_sha256":"5a29d60a7dbbaecca1e7be0929eb54c65d9f7cc6fbc8c8cf0d3ffe98fc5bfaa4","source":{"kind":"arxiv","id":"2403.10568","version":4},"attestation_state":"computed","paper":{"title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","license":"","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Changwen Chen, Lingbo Liu, Ruixiang Jiang","submitted_at":"2024-03-14T17:47:10Z","abstract_excerpt":"Despite the demonstrated parameter efficiency of prompt-based fusion, its limited adaptivity and expressiveness hinder its effectiveness for multimodal applications at scale. In this paper, we present the first comprehensive study addressing these limitations. Our key motivation is to ``divide and conquer'' the vanilla prompt, traditionally shared across all instances, by generating instance-specific prompts. Specifically, we propose the Mixture of Prompt Experts (MoPE), a framework that significantly enhances prompt adaptivity and expressiveness by dynamically generating instance-specific pro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":true,"weak_author_claims":0,"strong_author_claims":1,"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":"2403.10568","kind":"arxiv","version":4},"metadata":{"license":"","primary_cat":"cs.LG","submitted_at":"2024-03-14T17:47:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"0d0b36e3a0b588e95e96536ce0adaffe308d2052d424e69134dc0af6ca704f4f","abstract_canon_sha256":"617eaaf0383c03cdd3ccb02a56a9d63828c5655c35833c3add81b9d6e94fca7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-28T15:26:20.061556Z","signature_b64":"i0tuz2QjqA0/Ad//JVgQHwQgKUQwH016OmLgbu3e4uEvYl9P1JynYG4O/P6XtE/2S4FccYeddHMFnzjvbhYyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a29d60a7dbbaecca1e7be0929eb54c65d9f7cc6fbc8c8cf0d3ffe98fc5bfaa4","last_reissued_at":"2026-06-28T15:26:20.061040Z","signature_status":"signed_v1","first_computed_at":"2026-06-28T15:26:20.061040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","license":"","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Changwen Chen, Lingbo Liu, Ruixiang Jiang","submitted_at":"2024-03-14T17:47:10Z","abstract_excerpt":"Despite the demonstrated parameter efficiency of prompt-based fusion, its limited adaptivity and expressiveness hinder its effectiveness for multimodal applications at scale. In this paper, we present the first comprehensive study addressing these limitations. Our key motivation is to ``divide and conquer'' the vanilla prompt, traditionally shared across all instances, by generating instance-specific prompts. Specifically, we propose the Mixture of Prompt Experts (MoPE), a framework that significantly enhances prompt adaptivity and expressiveness by dynamically generating instance-specific pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10568","kind":"arxiv","version":4},"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/2403.10568/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":"2403.10568","created_at":"2026-06-28T15:26:20.061099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10568v4","created_at":"2026-06-28T15:26:20.061099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10568","created_at":"2026-06-28T15:26:20.061099+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIU5MCT5XOXM","created_at":"2026-06-28T15:26:20.061099+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIU5MCT5XOXMZIPH","created_at":"2026-06-28T15:26:20.061099+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIU5MCT5","created_at":"2026-06-28T15:26:20.061099+00:00"}],"events":[],"event_summary":{},"paper_claims":[{"claim_id":"ac4e08b6-202d-4163-b27d-ad6009ead26b","handle":null,"display_name":"JIANG Ruixiang","verification":"orcid_verified","verification_note":"Auto-claimed from ORCID 0000-0001-8666-6767 at registration","role_label":null,"open_disputes":0}],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ","json":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ.json","graph_json":"https://pith.science/api/pith-number/LIU5MCT5XOXMZIPHXYEST22UYZ/graph.json","events_json":"https://pith.science/api/pith-number/LIU5MCT5XOXMZIPHXYEST22UYZ/events.json","paper":"https://pith.science/paper/LIU5MCT5"},"agent_actions":{"view_html":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ","download_json":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ.json","view_paper":"https://pith.science/paper/LIU5MCT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10568&json=true","fetch_graph":"https://pith.science/api/pith-number/LIU5MCT5XOXMZIPHXYEST22UYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LIU5MCT5XOXMZIPHXYEST22UYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ/action/storage_attestation","attest_author":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ/action/author_attestation","sign_citation":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ/action/citation_signature","submit_replication":"https://pith.science/pith/LIU5MCT5XOXMZIPHXYEST22UYZ/action/replication_record"}},"created_at":"2026-06-28T15:26:20.061099+00:00","updated_at":"2026-06-28T15:26:20.061099+00:00"}