{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PXQ57DER6M7EO5XRTZX3X5BCCF","short_pith_number":"pith:PXQ57DER","schema_version":"1.0","canonical_sha256":"7de1df8c91f33e4776f19e6fbbf422114e2f6e8570f369d64aa2f06339782f0d","source":{"kind":"arxiv","id":"2410.20178","version":2},"attestation_state":"computed","paper":{"title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dong Wang, Haiwen Diao, Haomiao Xiong, Huchuan Lu, Jiazuo Yu, Lanqing Hong, Long Chen, Lu Zhang, You He, Yunzhi Zhuge","submitted_at":"2024-10-26T13:19:57Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have gained significant attention due to their impressive capabilities in multimodal understanding. However, existing methods rely heavily on extensive modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. In this paper, we propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities that enables MLLMs to continually EVolve on modalities for $\\mathbb{X}$-modal reasoning. We leverage the concept of Continual Learning and develop an increm"},"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":"2410.20178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-26T13:19:57Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"319320a9dc73b61493f5a87a20652f82a7cd800057389a6aa987502def87241e","abstract_canon_sha256":"a2ab0822b747773415d82f058cb75341036cc78241fd20174622cb275db788be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:21.426059Z","signature_b64":"OM0w9yXhd8Nzrk4EqPKJXhmfRMdHMlfgLlyHwx7YjXQf7UffK89OAv1w3wxcBbzwRoynt3/OF5G8JGtw7liDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7de1df8c91f33e4776f19e6fbbf422114e2f6e8570f369d64aa2f06339782f0d","last_reissued_at":"2026-07-05T09:34:21.425539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:21.425539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dong Wang, Haiwen Diao, Haomiao Xiong, Huchuan Lu, Jiazuo Yu, Lanqing Hong, Long Chen, Lu Zhang, You He, Yunzhi Zhuge","submitted_at":"2024-10-26T13:19:57Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have gained significant attention due to their impressive capabilities in multimodal understanding. However, existing methods rely heavily on extensive modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. In this paper, we propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities that enables MLLMs to continually EVolve on modalities for $\\mathbb{X}$-modal reasoning. We leverage the concept of Continual Learning and develop an increm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20178","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/2410.20178/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":"2410.20178","created_at":"2026-07-05T09:34:21.425603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20178v2","created_at":"2026-07-05T09:34:21.425603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20178","created_at":"2026-07-05T09:34:21.425603+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXQ57DER6M7E","created_at":"2026-07-05T09:34:21.425603+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXQ57DER6M7EO5XR","created_at":"2026-07-05T09:34:21.425603+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXQ57DER","created_at":"2026-07-05T09:34:21.425603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04606","citing_title":"Sample-efficient Integration of New Modalities into Large Language Models","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF","json":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF.json","graph_json":"https://pith.science/api/pith-number/PXQ57DER6M7EO5XRTZX3X5BCCF/graph.json","events_json":"https://pith.science/api/pith-number/PXQ57DER6M7EO5XRTZX3X5BCCF/events.json","paper":"https://pith.science/paper/PXQ57DER"},"agent_actions":{"view_html":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF","download_json":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF.json","view_paper":"https://pith.science/paper/PXQ57DER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20178&json=true","fetch_graph":"https://pith.science/api/pith-number/PXQ57DER6M7EO5XRTZX3X5BCCF/graph.json","fetch_events":"https://pith.science/api/pith-number/PXQ57DER6M7EO5XRTZX3X5BCCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF/action/storage_attestation","attest_author":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF/action/author_attestation","sign_citation":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF/action/citation_signature","submit_replication":"https://pith.science/pith/PXQ57DER6M7EO5XRTZX3X5BCCF/action/replication_record"}},"created_at":"2026-07-05T09:34:21.425603+00:00","updated_at":"2026-07-05T09:34:21.425603+00:00"}