{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TIPIFIILMQQ6JR3PRN3DU5LZPV","short_pith_number":"pith:TIPIFIIL","schema_version":"1.0","canonical_sha256":"9a1e82a10b6421e4c76f8b763a75797d4306cd23b0043a46b973a63383e11b14","source":{"kind":"arxiv","id":"2403.13600","version":1},"attestation_state":"computed","paper":{"title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Longteng Guo, Mingzhen Sun, Qi Wu, Sihan Chen, Yanyuan Qiao, Zheng Yu, Zijia Zhao","submitted_at":"2024-03-20T13:48:50Z","abstract_excerpt":"Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in expensive computational overhead. Therefore, in this work, we propose VL-Mamba, a multimodal large language model based on state space models, which have been shown to have great potential for long-sequence modeling with fast inference and linear scaling in sequence length. Specifically, we first replace the transformer-based backbone language model such as LLama or Vicuna with"},"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":"2403.13600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T13:48:50Z","cross_cats_sorted":[],"title_canon_sha256":"2b1d135d6edd93e79bb6a727454bb02795b8ff8ebfeccdfac4ffac4927af91b3","abstract_canon_sha256":"7306b2413ab42b9407b5c0a144bcc7418d81108a189547e85dc122a0d050df1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:39.306822Z","signature_b64":"XiGIbcwD938spU8SXj09MflxOVaYeaGDmtNT57OXPhbhKekOLhTonM5saqyIuTdUdUzFT0SVweQaMeTuuP2GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a1e82a10b6421e4c76f8b763a75797d4306cd23b0043a46b973a63383e11b14","last_reissued_at":"2026-07-05T07:58:39.306244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:39.306244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Longteng Guo, Mingzhen Sun, Qi Wu, Sihan Chen, Yanyuan Qiao, Zheng Yu, Zijia Zhao","submitted_at":"2024-03-20T13:48:50Z","abstract_excerpt":"Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in expensive computational overhead. Therefore, in this work, we propose VL-Mamba, a multimodal large language model based on state space models, which have been shown to have great potential for long-sequence modeling with fast inference and linear scaling in sequence length. Specifically, we first replace the transformer-based backbone language model such as LLama or Vicuna with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13600","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/2403.13600/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":"2403.13600","created_at":"2026-07-05T07:58:39.306305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13600v1","created_at":"2026-07-05T07:58:39.306305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13600","created_at":"2026-07-05T07:58:39.306305+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIPIFIILMQQ6","created_at":"2026-07-05T07:58:39.306305+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIPIFIILMQQ6JR3P","created_at":"2026-07-05T07:58:39.306305+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIPIFIIL","created_at":"2026-07-05T07:58:39.306305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23126","citing_title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00390","citing_title":"Zamba2-VL Technical Report","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2503.18970","citing_title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01322","citing_title":"LinMU: Multimodal Understanding Made Linear","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08050","citing_title":"ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08073","citing_title":"EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV","json":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV.json","graph_json":"https://pith.science/api/pith-number/TIPIFIILMQQ6JR3PRN3DU5LZPV/graph.json","events_json":"https://pith.science/api/pith-number/TIPIFIILMQQ6JR3PRN3DU5LZPV/events.json","paper":"https://pith.science/paper/TIPIFIIL"},"agent_actions":{"view_html":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV","download_json":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV.json","view_paper":"https://pith.science/paper/TIPIFIIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13600&json=true","fetch_graph":"https://pith.science/api/pith-number/TIPIFIILMQQ6JR3PRN3DU5LZPV/graph.json","fetch_events":"https://pith.science/api/pith-number/TIPIFIILMQQ6JR3PRN3DU5LZPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV/action/storage_attestation","attest_author":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV/action/author_attestation","sign_citation":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV/action/citation_signature","submit_replication":"https://pith.science/pith/TIPIFIILMQQ6JR3PRN3DU5LZPV/action/replication_record"}},"created_at":"2026-07-05T07:58:39.306305+00:00","updated_at":"2026-07-05T07:58:39.306305+00:00"}