{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CY6V7C3CCNPJDSVTNQYXKQKKUN","short_pith_number":"pith:CY6V7C3C","schema_version":"1.0","canonical_sha256":"163d5f8b62135e91cab36c3175414aa34700c4d212ee7e6f52cc5a24cb3cbd73","source":{"kind":"arxiv","id":"2401.03105","version":2},"attestation_state":"computed","paper":{"title":"Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Lingxi Xie, Longhui Wei, Qi Tian, Xin He","submitted_at":"2024-01-06T02:02:34Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months. The prevailing trend involves adopting data-driven methodologies, wherein diverse instruction-following datasets are collected. However, a prevailing challenge persists in these approaches, specifically in relation to the limited visual perception ability, as CLIP-like encoders employed for extracting visual information from inputs. Though these encoders are pre-trained on billions of image-text pairs, they still grapple with the information loss dilemma, gi"},"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":"2401.03105","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T02:02:34Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e91d55267b99a37ccf138a5e93ed5edf07e69b5bcb3df9d7c23963accb999703","abstract_canon_sha256":"d72585bf496a64150aa391cf8202115276d3e0708f66d726d279088a16f6e9df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:25.456657Z","signature_b64":"903BChijvHkhxYgLCQbqJY5wB7CYwA3/yLoJcUHFejrm4dghbhJZlK6KKpNc2/JotLB/xh7paR1pHZLTNZ15DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"163d5f8b62135e91cab36c3175414aa34700c4d212ee7e6f52cc5a24cb3cbd73","last_reissued_at":"2026-07-05T07:33:25.456154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:25.456154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Lingxi Xie, Longhui Wei, Qi Tian, Xin He","submitted_at":"2024-01-06T02:02:34Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months. The prevailing trend involves adopting data-driven methodologies, wherein diverse instruction-following datasets are collected. However, a prevailing challenge persists in these approaches, specifically in relation to the limited visual perception ability, as CLIP-like encoders employed for extracting visual information from inputs. Though these encoders are pre-trained on billions of image-text pairs, they still grapple with the information loss dilemma, gi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03105","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/2401.03105/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":"2401.03105","created_at":"2026-07-05T07:33:25.456225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03105v2","created_at":"2026-07-05T07:33:25.456225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03105","created_at":"2026-07-05T07:33:25.456225+00:00"},{"alias_kind":"pith_short_12","alias_value":"CY6V7C3CCNPJ","created_at":"2026-07-05T07:33:25.456225+00:00"},{"alias_kind":"pith_short_16","alias_value":"CY6V7C3CCNPJDSVT","created_at":"2026-07-05T07:33:25.456225+00:00"},{"alias_kind":"pith_short_8","alias_value":"CY6V7C3C","created_at":"2026-07-05T07:33:25.456225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN","json":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN.json","graph_json":"https://pith.science/api/pith-number/CY6V7C3CCNPJDSVTNQYXKQKKUN/graph.json","events_json":"https://pith.science/api/pith-number/CY6V7C3CCNPJDSVTNQYXKQKKUN/events.json","paper":"https://pith.science/paper/CY6V7C3C"},"agent_actions":{"view_html":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN","download_json":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN.json","view_paper":"https://pith.science/paper/CY6V7C3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03105&json=true","fetch_graph":"https://pith.science/api/pith-number/CY6V7C3CCNPJDSVTNQYXKQKKUN/graph.json","fetch_events":"https://pith.science/api/pith-number/CY6V7C3CCNPJDSVTNQYXKQKKUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN/action/storage_attestation","attest_author":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN/action/author_attestation","sign_citation":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN/action/citation_signature","submit_replication":"https://pith.science/pith/CY6V7C3CCNPJDSVTNQYXKQKKUN/action/replication_record"}},"created_at":"2026-07-05T07:33:25.456225+00:00","updated_at":"2026-07-05T07:33:25.456225+00:00"}