{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JI2YAATOKQG3BHXHJ3UT73NYD5","short_pith_number":"pith:JI2YAATO","schema_version":"1.0","canonical_sha256":"4a3580026e540db09ee74ee93fedb81f4fded67f3078d33460b71fea72546951","source":{"kind":"arxiv","id":"2408.12321","version":2},"attestation_state":"computed","paper":{"title":"MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Jia Hongrui, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","submitted_at":"2024-08-22T11:57:16Z","abstract_excerpt":"This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. Current MLLMs primarily focus on single-image visual understanding, limiting their ability to interpret and integrate information across multiple images. MaVEn addresses this limitation by combining discrete visual symbol sequences, which abstract coarse-grained semantic concepts, with traditional continuous representation sequences that model fine-grained features. This dual approach bridges the semantic"},"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":"2408.12321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T11:57:16Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"e48d673e5b900dfdf2f85a7a5f03b478989b17d3a3dcbe16f1b5334d9658dc1a","abstract_canon_sha256":"958a9b3ce5ece64f6d9f40c6dc11ebe46c510295f7b49a05adad61d8299b313e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:12.337860Z","signature_b64":"K2uXt1akqIFUUcBQQDjCNKq2iuyx1NFz7U9eIeDj5AuEhHSymS/fbrggf1p/RumAXJ7qjALxwj2pFpsM5EHbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3580026e540db09ee74ee93fedb81f4fded67f3078d33460b71fea72546951","last_reissued_at":"2026-07-05T08:59:12.337410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:12.337410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Chaoya Jiang, Fei Huang, Haiyang Xu, Jia Hongrui, Ji Zhang, Mengfan Dong, Ming Yan, Shikun Zhang, Wei Ye","submitted_at":"2024-08-22T11:57:16Z","abstract_excerpt":"This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. Current MLLMs primarily focus on single-image visual understanding, limiting their ability to interpret and integrate information across multiple images. MaVEn addresses this limitation by combining discrete visual symbol sequences, which abstract coarse-grained semantic concepts, with traditional continuous representation sequences that model fine-grained features. This dual approach bridges the semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12321","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/2408.12321/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":"2408.12321","created_at":"2026-07-05T08:59:12.337468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12321v2","created_at":"2026-07-05T08:59:12.337468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12321","created_at":"2026-07-05T08:59:12.337468+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI2YAATOKQG3","created_at":"2026-07-05T08:59:12.337468+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI2YAATOKQG3BHXH","created_at":"2026-07-05T08:59:12.337468+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI2YAATO","created_at":"2026-07-05T08:59:12.337468+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/JI2YAATOKQG3BHXHJ3UT73NYD5","json":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5.json","graph_json":"https://pith.science/api/pith-number/JI2YAATOKQG3BHXHJ3UT73NYD5/graph.json","events_json":"https://pith.science/api/pith-number/JI2YAATOKQG3BHXHJ3UT73NYD5/events.json","paper":"https://pith.science/paper/JI2YAATO"},"agent_actions":{"view_html":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5","download_json":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5.json","view_paper":"https://pith.science/paper/JI2YAATO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12321&json=true","fetch_graph":"https://pith.science/api/pith-number/JI2YAATOKQG3BHXHJ3UT73NYD5/graph.json","fetch_events":"https://pith.science/api/pith-number/JI2YAATOKQG3BHXHJ3UT73NYD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/action/storage_attestation","attest_author":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/action/author_attestation","sign_citation":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/action/citation_signature","submit_replication":"https://pith.science/pith/JI2YAATOKQG3BHXHJ3UT73NYD5/action/replication_record"}},"created_at":"2026-07-05T08:59:12.337468+00:00","updated_at":"2026-07-05T08:59:12.337468+00:00"}