{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SIUTZ57DZBHUBJ65G5P6HBLPQS","short_pith_number":"pith:SIUTZ57D","schema_version":"1.0","canonical_sha256":"92293cf7e3c84f40a7dd375fe3856f84a173cc00f6d3ada53149a246a7669500","source":{"kind":"arxiv","id":"2406.05130","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyao Zhu, Jeff Z. Pan, Jie He, V\\'ictor Guti\\'errez-Basulto, Xiongtao Zhou, Yuhua Ke","submitted_at":"2024-06-07T17:58:11Z","abstract_excerpt":"Multimodal large language models (MLLMs) fine-tuned with multimodal instruction datasets have demonstrated remarkable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging as they usually contain billions of parameters. To address this issue, we study parameter-efficient fine-tuning (PEFT) methods for MLLMs. We aim to identify effective methods for enhancing the performance of MLLMs in scenarios where only a limited number of parameters are trained. This paper conducts empirical studies using four popular PEFT methods to fine-tune the LLM compone"},"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":"2406.05130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T17:58:11Z","cross_cats_sorted":[],"title_canon_sha256":"78d4a27551f18003e0f9ce611042562e5c28b0d1b2cc19413722f94d9cca5522","abstract_canon_sha256":"96c0c05203fb8f9d22f9535b6a68e272a7f4f16e3fb0871b45dbe7dfd4a5fbdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:54.811059Z","signature_b64":"0r2m9slhGWs4f/Jg73D1FfXj7CbCznpD7e4FqKOOdB09tPyEyZjJquNCDCtI/dZLp9/bCyONitiTlsJSLqm4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92293cf7e3c84f40a7dd375fe3856f84a173cc00f6d3ada53149a246a7669500","last_reissued_at":"2026-07-05T08:28:54.810598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:54.810598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyao Zhu, Jeff Z. Pan, Jie He, V\\'ictor Guti\\'errez-Basulto, Xiongtao Zhou, Yuhua Ke","submitted_at":"2024-06-07T17:58:11Z","abstract_excerpt":"Multimodal large language models (MLLMs) fine-tuned with multimodal instruction datasets have demonstrated remarkable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging as they usually contain billions of parameters. To address this issue, we study parameter-efficient fine-tuning (PEFT) methods for MLLMs. We aim to identify effective methods for enhancing the performance of MLLMs in scenarios where only a limited number of parameters are trained. This paper conducts empirical studies using four popular PEFT methods to fine-tune the LLM compone"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05130","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/2406.05130/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":"2406.05130","created_at":"2026-07-05T08:28:54.810654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05130v1","created_at":"2026-07-05T08:28:54.810654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05130","created_at":"2026-07-05T08:28:54.810654+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIUTZ57DZBHU","created_at":"2026-07-05T08:28:54.810654+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIUTZ57DZBHUBJ65","created_at":"2026-07-05T08:28:54.810654+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIUTZ57D","created_at":"2026-07-05T08:28:54.810654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02014","citing_title":"Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimization","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS","json":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS.json","graph_json":"https://pith.science/api/pith-number/SIUTZ57DZBHUBJ65G5P6HBLPQS/graph.json","events_json":"https://pith.science/api/pith-number/SIUTZ57DZBHUBJ65G5P6HBLPQS/events.json","paper":"https://pith.science/paper/SIUTZ57D"},"agent_actions":{"view_html":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS","download_json":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS.json","view_paper":"https://pith.science/paper/SIUTZ57D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05130&json=true","fetch_graph":"https://pith.science/api/pith-number/SIUTZ57DZBHUBJ65G5P6HBLPQS/graph.json","fetch_events":"https://pith.science/api/pith-number/SIUTZ57DZBHUBJ65G5P6HBLPQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS/action/storage_attestation","attest_author":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS/action/author_attestation","sign_citation":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS/action/citation_signature","submit_replication":"https://pith.science/pith/SIUTZ57DZBHUBJ65G5P6HBLPQS/action/replication_record"}},"created_at":"2026-07-05T08:28:54.810654+00:00","updated_at":"2026-07-05T08:28:54.810654+00:00"}