{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FD6OCEEYT46H76DRDHI2XVYGAF","short_pith_number":"pith:FD6OCEEY","schema_version":"1.0","canonical_sha256":"28fce110989f3c7ff87119d1abd706014e89d6c3b8f0e97449839808c2f4fea1","source":{"kind":"arxiv","id":"2606.04719","version":1},"attestation_state":"computed","paper":{"title":"Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang D. Yoo, Gwanhyeong Koo, Haebin Na, Jay Shim, Mark A. Hasegawa-Johnson, SooHwan Eom, Sungwoong Kim","submitted_at":"2026-06-03T10:56:56Z","abstract_excerpt":"The Transformer's quadratic complexity with input length imposes an unsustainable computational load on large language models (LLMs). In contrast, the Selective Scan Structured State-Space Model, or Mamba, addresses this computational challenge effectively. This paper explores a query-based cross-modal projector designed to bolster Mamba's efficiency for vision-language modeling by compressing visual tokens based on input through the cross-attention mechanism. This innovative projector also removes the need for manually designing the 2D scan order of original image features when converting the"},"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":"2606.04719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T10:56:56Z","cross_cats_sorted":[],"title_canon_sha256":"8cf771a760d554bd498780b8bfb2a3fbca168fdb33e637ec71c3425cbdc5acd3","abstract_canon_sha256":"5425e33d2d9f2241ae764143ca942152cc313abda3ba6bb8551dcc4bc2a395ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:26.624215Z","signature_b64":"iLOrt4jOSCU6Ja2MEh69xP4RReEkqKPgl9iljFh1h6bDwZWGvd3lV14KlPBu6nID5fPTt29ja5IklbKgx3XUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28fce110989f3c7ff87119d1abd706014e89d6c3b8f0e97449839808c2f4fea1","last_reissued_at":"2026-06-04T01:09:26.623507Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:26.623507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang D. Yoo, Gwanhyeong Koo, Haebin Na, Jay Shim, Mark A. Hasegawa-Johnson, SooHwan Eom, Sungwoong Kim","submitted_at":"2026-06-03T10:56:56Z","abstract_excerpt":"The Transformer's quadratic complexity with input length imposes an unsustainable computational load on large language models (LLMs). In contrast, the Selective Scan Structured State-Space Model, or Mamba, addresses this computational challenge effectively. This paper explores a query-based cross-modal projector designed to bolster Mamba's efficiency for vision-language modeling by compressing visual tokens based on input through the cross-attention mechanism. This innovative projector also removes the need for manually designing the 2D scan order of original image features when converting the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04719","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/2606.04719/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":"2606.04719","created_at":"2026-06-04T01:09:26.623632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04719v1","created_at":"2026-06-04T01:09:26.623632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04719","created_at":"2026-06-04T01:09:26.623632+00:00"},{"alias_kind":"pith_short_12","alias_value":"FD6OCEEYT46H","created_at":"2026-06-04T01:09:26.623632+00:00"},{"alias_kind":"pith_short_16","alias_value":"FD6OCEEYT46H76DR","created_at":"2026-06-04T01:09:26.623632+00:00"},{"alias_kind":"pith_short_8","alias_value":"FD6OCEEY","created_at":"2026-06-04T01:09:26.623632+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/FD6OCEEYT46H76DRDHI2XVYGAF","json":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF.json","graph_json":"https://pith.science/api/pith-number/FD6OCEEYT46H76DRDHI2XVYGAF/graph.json","events_json":"https://pith.science/api/pith-number/FD6OCEEYT46H76DRDHI2XVYGAF/events.json","paper":"https://pith.science/paper/FD6OCEEY"},"agent_actions":{"view_html":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF","download_json":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF.json","view_paper":"https://pith.science/paper/FD6OCEEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04719&json=true","fetch_graph":"https://pith.science/api/pith-number/FD6OCEEYT46H76DRDHI2XVYGAF/graph.json","fetch_events":"https://pith.science/api/pith-number/FD6OCEEYT46H76DRDHI2XVYGAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF/action/storage_attestation","attest_author":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF/action/author_attestation","sign_citation":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF/action/citation_signature","submit_replication":"https://pith.science/pith/FD6OCEEYT46H76DRDHI2XVYGAF/action/replication_record"}},"created_at":"2026-06-04T01:09:26.623632+00:00","updated_at":"2026-06-04T01:09:26.623632+00:00"}