{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TGK5BXU575XB4DE3W6UNMD2GD5","short_pith_number":"pith:TGK5BXU5","schema_version":"1.0","canonical_sha256":"9995d0de9dff6e1e0c9bb7a8d60f461f4d78a064baddba64d2406c00d3a222ce","source":{"kind":"arxiv","id":"2505.19455","version":2},"attestation_state":"computed","paper":{"title":"MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Lyu, Xu Li","submitted_at":"2025-05-26T03:21:21Z","abstract_excerpt":"Continual Visual Question Answering (CVQA) based on pre-trained models(PTMs) has achieved promising progress by leveraging prompt tuning to enable continual multi-modal learning. However, most existing methods adopt cross-modal prompt isolation, constructing visual and textual prompts separately, which exacerbates modality imbalance and leads to degraded performance over time. To tackle this issue, we propose MM-Prompt, a novel framework incorporating cross-modal prompt query and cross-modal prompt recovery. The former enables balanced prompt selection by incorporating cross-modal signals duri"},"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":"2505.19455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T03:21:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7d62eebd754fffe13b18d1ba4399411f389a0ec09148517fc0e64d5f785a2ab0","abstract_canon_sha256":"fcb7a7be345d3cb4e4f17a80cd566614568b2dd331aa8793ff33b890fb5e75a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:18.182180Z","signature_b64":"ObXBYqq+vEOhWUQkkm6yPGwf25ISrgP03K/diuKybqLx9+EprLt62oGAhdIZMLt8vKLyMtOdv+jB1pOR6I+7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9995d0de9dff6e1e0c9bb7a8d60f461f4d78a064baddba64d2406c00d3a222ce","last_reissued_at":"2026-07-05T12:09:18.181746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:18.181746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Lyu, Xu Li","submitted_at":"2025-05-26T03:21:21Z","abstract_excerpt":"Continual Visual Question Answering (CVQA) based on pre-trained models(PTMs) has achieved promising progress by leveraging prompt tuning to enable continual multi-modal learning. However, most existing methods adopt cross-modal prompt isolation, constructing visual and textual prompts separately, which exacerbates modality imbalance and leads to degraded performance over time. To tackle this issue, we propose MM-Prompt, a novel framework incorporating cross-modal prompt query and cross-modal prompt recovery. The former enables balanced prompt selection by incorporating cross-modal signals duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19455","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/2505.19455/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":"2505.19455","created_at":"2026-07-05T12:09:18.181803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19455v2","created_at":"2026-07-05T12:09:18.181803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19455","created_at":"2026-07-05T12:09:18.181803+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGK5BXU575XB","created_at":"2026-07-05T12:09:18.181803+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGK5BXU575XB4DE3","created_at":"2026-07-05T12:09:18.181803+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGK5BXU5","created_at":"2026-07-05T12:09:18.181803+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/TGK5BXU575XB4DE3W6UNMD2GD5","json":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5.json","graph_json":"https://pith.science/api/pith-number/TGK5BXU575XB4DE3W6UNMD2GD5/graph.json","events_json":"https://pith.science/api/pith-number/TGK5BXU575XB4DE3W6UNMD2GD5/events.json","paper":"https://pith.science/paper/TGK5BXU5"},"agent_actions":{"view_html":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5","download_json":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5.json","view_paper":"https://pith.science/paper/TGK5BXU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19455&json=true","fetch_graph":"https://pith.science/api/pith-number/TGK5BXU575XB4DE3W6UNMD2GD5/graph.json","fetch_events":"https://pith.science/api/pith-number/TGK5BXU575XB4DE3W6UNMD2GD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5/action/storage_attestation","attest_author":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5/action/author_attestation","sign_citation":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5/action/citation_signature","submit_replication":"https://pith.science/pith/TGK5BXU575XB4DE3W6UNMD2GD5/action/replication_record"}},"created_at":"2026-07-05T12:09:18.181803+00:00","updated_at":"2026-07-05T12:09:18.181803+00:00"}