{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLANPCCUMRWKBGBGHTZ5XEF7JI","short_pith_number":"pith:KLANPCCU","schema_version":"1.0","canonical_sha256":"52c0d78854646ca098263cf3db90bf4a04b50fb26752a6a2ac1ddf3db5b5a46a","source":{"kind":"arxiv","id":"2410.05938","version":1},"attestation_state":"computed","paper":{"title":"EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongmei Jiang, Qingfang Zheng, Ruiping Wang, Wenjun Huang, Xiangyuan Lan, Yaowei Wang, Yifei Xing","submitted_at":"2024-10-08T11:41:55Z","abstract_excerpt":"Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are insufficient in extracting visual features, leading to imbalanced cross-modal alignment between visual and textural latents, negatively impacting performance on multi-modal tasks. In this work, we propose Empowering Multi-modal Mamba with Structural and Hierarchical Alignment (EMMA), which enables the MLLM to extract fine-grained visual information. Specificall"},"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":"2410.05938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T11:41:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67f262123538ff5339397348e0a7a4dcdb3590f2c8b806fbb8c76ecac1baa48f","abstract_canon_sha256":"5d75028d5d3c4f97ea9cf43f83be591145fc3a57740cb9c5ced388696f255321"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:53.335870Z","signature_b64":"nStrUiBY639N1o1CxnZkwM7NA+aYwJrgwjlT9QHCBqRCW6G3Zk/pAfLNaMfwaMSM6xiBdUh/lQBZVM5Ei824Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c0d78854646ca098263cf3db90bf4a04b50fb26752a6a2ac1ddf3db5b5a46a","last_reissued_at":"2026-07-05T09:17:53.335164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:53.335164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongmei Jiang, Qingfang Zheng, Ruiping Wang, Wenjun Huang, Xiangyuan Lan, Yaowei Wang, Yifei Xing","submitted_at":"2024-10-08T11:41:55Z","abstract_excerpt":"Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are insufficient in extracting visual features, leading to imbalanced cross-modal alignment between visual and textural latents, negatively impacting performance on multi-modal tasks. In this work, we propose Empowering Multi-modal Mamba with Structural and Hierarchical Alignment (EMMA), which enables the MLLM to extract fine-grained visual information. Specificall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05938","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/2410.05938/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":"2410.05938","created_at":"2026-07-05T09:17:53.335226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05938v1","created_at":"2026-07-05T09:17:53.335226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05938","created_at":"2026-07-05T09:17:53.335226+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLANPCCUMRWK","created_at":"2026-07-05T09:17:53.335226+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLANPCCUMRWKBGBG","created_at":"2026-07-05T09:17:53.335226+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLANPCCU","created_at":"2026-07-05T09:17:53.335226+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/KLANPCCUMRWKBGBGHTZ5XEF7JI","json":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI.json","graph_json":"https://pith.science/api/pith-number/KLANPCCUMRWKBGBGHTZ5XEF7JI/graph.json","events_json":"https://pith.science/api/pith-number/KLANPCCUMRWKBGBGHTZ5XEF7JI/events.json","paper":"https://pith.science/paper/KLANPCCU"},"agent_actions":{"view_html":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI","download_json":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI.json","view_paper":"https://pith.science/paper/KLANPCCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05938&json=true","fetch_graph":"https://pith.science/api/pith-number/KLANPCCUMRWKBGBGHTZ5XEF7JI/graph.json","fetch_events":"https://pith.science/api/pith-number/KLANPCCUMRWKBGBGHTZ5XEF7JI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI/action/storage_attestation","attest_author":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI/action/author_attestation","sign_citation":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI/action/citation_signature","submit_replication":"https://pith.science/pith/KLANPCCUMRWKBGBGHTZ5XEF7JI/action/replication_record"}},"created_at":"2026-07-05T09:17:53.335226+00:00","updated_at":"2026-07-05T09:17:53.335226+00:00"}