{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2I2GSVDKWWKRF4WG7XJGCHLXN4","short_pith_number":"pith:2I2GSVDK","schema_version":"1.0","canonical_sha256":"d23469546ab59512f2c6fdd2611d776f2b7f6b71039d2fb2a75cf95c2dd7f759","source":{"kind":"arxiv","id":"2506.11515","version":1},"attestation_state":"computed","paper":{"title":"Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Libo Qin, Min-Yen Kan, Wanxiang Che, Xiao Xu","submitted_at":"2025-06-13T07:16:41Z","abstract_excerpt":"Two-Tower Vision--Language Models (VLMs) have demonstrated strong performance across various downstream VL tasks. While BridgeTower further enhances performance by building bridges between encoders, it \\textit{(i)} suffers from ineffective layer-by-layer utilization of unimodal representations, \\textit{(ii)} restricts the flexible exploitation of different levels of unimodal semantic knowledge, and \\textit{(iii)} is limited to the evaluation on traditional low-resolution datasets only with the Two-Tower VLM architecture. In this work, we propose Manager, a lightweight, efficient and effective "},"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":"2506.11515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T07:16:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"429cdf3597de26e6599eab434d06c95c01c03d2d2060553f5e7a62cd6ad1d611","abstract_canon_sha256":"1362145a7baefb57fad380621e5aedb1dbd0f16b1c1baad4e3c4df472a85a278"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:05.899757Z","signature_b64":"mLruihpSnxsHkk+nfkfE6CpZGlkYhxD6/Tz3JUnoXGIQT921vLW5tyhPxBBe/RZ8dQT2g8Hm7Bdhz3xKD8wQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d23469546ab59512f2c6fdd2611d776f2b7f6b71039d2fb2a75cf95c2dd7f759","last_reissued_at":"2026-07-05T11:21:05.899257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:05.899257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Libo Qin, Min-Yen Kan, Wanxiang Che, Xiao Xu","submitted_at":"2025-06-13T07:16:41Z","abstract_excerpt":"Two-Tower Vision--Language Models (VLMs) have demonstrated strong performance across various downstream VL tasks. While BridgeTower further enhances performance by building bridges between encoders, it \\textit{(i)} suffers from ineffective layer-by-layer utilization of unimodal representations, \\textit{(ii)} restricts the flexible exploitation of different levels of unimodal semantic knowledge, and \\textit{(iii)} is limited to the evaluation on traditional low-resolution datasets only with the Two-Tower VLM architecture. In this work, we propose Manager, a lightweight, efficient and effective "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11515","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/2506.11515/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":"2506.11515","created_at":"2026-07-05T11:21:05.899322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11515v1","created_at":"2026-07-05T11:21:05.899322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11515","created_at":"2026-07-05T11:21:05.899322+00:00"},{"alias_kind":"pith_short_12","alias_value":"2I2GSVDKWWKR","created_at":"2026-07-05T11:21:05.899322+00:00"},{"alias_kind":"pith_short_16","alias_value":"2I2GSVDKWWKRF4WG","created_at":"2026-07-05T11:21:05.899322+00:00"},{"alias_kind":"pith_short_8","alias_value":"2I2GSVDK","created_at":"2026-07-05T11:21:05.899322+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/2I2GSVDKWWKRF4WG7XJGCHLXN4","json":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4.json","graph_json":"https://pith.science/api/pith-number/2I2GSVDKWWKRF4WG7XJGCHLXN4/graph.json","events_json":"https://pith.science/api/pith-number/2I2GSVDKWWKRF4WG7XJGCHLXN4/events.json","paper":"https://pith.science/paper/2I2GSVDK"},"agent_actions":{"view_html":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4","download_json":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4.json","view_paper":"https://pith.science/paper/2I2GSVDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11515&json=true","fetch_graph":"https://pith.science/api/pith-number/2I2GSVDKWWKRF4WG7XJGCHLXN4/graph.json","fetch_events":"https://pith.science/api/pith-number/2I2GSVDKWWKRF4WG7XJGCHLXN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/action/storage_attestation","attest_author":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/action/author_attestation","sign_citation":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/action/citation_signature","submit_replication":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/action/replication_record"}},"created_at":"2026-07-05T11:21:05.899322+00:00","updated_at":"2026-07-05T11:21:05.899322+00:00"}