{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SG7JEMZGD2GJBMQYGIVCO3LLAW","short_pith_number":"pith:SG7JEMZG","schema_version":"1.0","canonical_sha256":"91be9233261e8c90b218322a276d6b05bda5e567a65aab5d1a0dda1752438267","source":{"kind":"arxiv","id":"2501.16295","version":1},"attestation_state":"computed","paper":{"title":"Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Genghan Zhang, Junhong Shen, Lili Yu, Luke Zettlemoyer, Ning Dong, Weixin Liang","submitted_at":"2025-01-27T18:35:05Z","abstract_excerpt":"State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling, but their inability to leverage modality-specific features limits their performance in multi-modal pretraining. Here, we propose Mixture-of-Mamba, a novel SSM architecture that introduces modality-aware sparsity through modality-specific parameterization of the Mamba block. Building on Mixture-of-Transformers (W. Liang et al. arXiv:2411.04996; 2024), we extend the benefits of modality-aware sparsity to SSMs while preserving their computational efficiency. We evaluate Mixture-of-Mamba acros"},"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":"2501.16295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T18:35:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"256e2c956cfd8d20d4426178b8754120a31634e13d5ef1002ea9e4c81a6731b6","abstract_canon_sha256":"1f25a3262da2281bee76822cd7f442b11640a4e95af6ec3793d7bcb1e872176f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:58.160001Z","signature_b64":"P2ftgF+I1z2LrNHjxWs86QBVSTUX08LX+d5yZGJhnDp8TgTR2EnGRPVfDTuR5/0+0p8krM7cYGpQQwYgso/xCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91be9233261e8c90b218322a276d6b05bda5e567a65aab5d1a0dda1752438267","last_reissued_at":"2026-07-05T10:05:58.159523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:58.159523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Genghan Zhang, Junhong Shen, Lili Yu, Luke Zettlemoyer, Ning Dong, Weixin Liang","submitted_at":"2025-01-27T18:35:05Z","abstract_excerpt":"State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling, but their inability to leverage modality-specific features limits their performance in multi-modal pretraining. Here, we propose Mixture-of-Mamba, a novel SSM architecture that introduces modality-aware sparsity through modality-specific parameterization of the Mamba block. Building on Mixture-of-Transformers (W. Liang et al. arXiv:2411.04996; 2024), we extend the benefits of modality-aware sparsity to SSMs while preserving their computational efficiency. We evaluate Mixture-of-Mamba acros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16295","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/2501.16295/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":"2501.16295","created_at":"2026-07-05T10:05:58.159582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16295v1","created_at":"2026-07-05T10:05:58.159582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16295","created_at":"2026-07-05T10:05:58.159582+00:00"},{"alias_kind":"pith_short_12","alias_value":"SG7JEMZGD2GJ","created_at":"2026-07-05T10:05:58.159582+00:00"},{"alias_kind":"pith_short_16","alias_value":"SG7JEMZGD2GJBMQY","created_at":"2026-07-05T10:05:58.159582+00:00"},{"alias_kind":"pith_short_8","alias_value":"SG7JEMZG","created_at":"2026-07-05T10:05:58.159582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07976","citing_title":"Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW","json":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW.json","graph_json":"https://pith.science/api/pith-number/SG7JEMZGD2GJBMQYGIVCO3LLAW/graph.json","events_json":"https://pith.science/api/pith-number/SG7JEMZGD2GJBMQYGIVCO3LLAW/events.json","paper":"https://pith.science/paper/SG7JEMZG"},"agent_actions":{"view_html":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW","download_json":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW.json","view_paper":"https://pith.science/paper/SG7JEMZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16295&json=true","fetch_graph":"https://pith.science/api/pith-number/SG7JEMZGD2GJBMQYGIVCO3LLAW/graph.json","fetch_events":"https://pith.science/api/pith-number/SG7JEMZGD2GJBMQYGIVCO3LLAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW/action/storage_attestation","attest_author":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW/action/author_attestation","sign_citation":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW/action/citation_signature","submit_replication":"https://pith.science/pith/SG7JEMZGD2GJBMQYGIVCO3LLAW/action/replication_record"}},"created_at":"2026-07-05T10:05:58.159582+00:00","updated_at":"2026-07-05T10:05:58.159582+00:00"}