{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2WYPRYD2IAZCZ7FJODIUOQ4RWF","short_pith_number":"pith:2WYPRYD2","schema_version":"1.0","canonical_sha256":"d5b0f8e07a40322cfca970d1474391b1546f5b28046095b13546a566ec11b117","source":{"kind":"arxiv","id":"2507.17436","version":1},"attestation_state":"computed","paper":{"title":"Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Zheng, Minghe Weng, Ping Lu, Rui Jiang, Wei Su, Xi Li, Yehao Lu, Zekang Xiao","submitted_at":"2025-07-23T11:51:06Z","abstract_excerpt":"The Mixture of Experts (MoE) architecture has excelled in Large Vision-Language Models (LVLMs), yet its potential in real-time open-vocabulary object detectors, which also leverage large-scale vision-language datasets but smaller models, remains unexplored. This work investigates this domain, revealing intriguing insights. In the shallow layers, experts tend to cooperate with diverse peers to expand the search space. While in the deeper layers, fixed collaborative structures emerge, where each expert maintains 2-3 fixed partners and distinct expert combinations are specialized in processing sp"},"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":"2507.17436","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-23T11:51:06Z","cross_cats_sorted":[],"title_canon_sha256":"938148e6ba1a52df230dd98aeaaa4720bfc431f6fd4230f52b49193e98f0faa1","abstract_canon_sha256":"14375a9f55bc2c9ac1066add3f21b4f1a8e63434cccd35bf4e82561dc46472ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:07.592431Z","signature_b64":"PJCw6SeZRaw2MZPiI5rp7Mpn0RpfPCVpHuwEb3QlXBCTIubPFLe/509TTsMpJpeogCltwTvLVv5VAE9xukrvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5b0f8e07a40322cfca970d1474391b1546f5b28046095b13546a566ec11b117","last_reissued_at":"2026-07-05T11:42:07.591901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:07.591901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Zheng, Minghe Weng, Ping Lu, Rui Jiang, Wei Su, Xi Li, Yehao Lu, Zekang Xiao","submitted_at":"2025-07-23T11:51:06Z","abstract_excerpt":"The Mixture of Experts (MoE) architecture has excelled in Large Vision-Language Models (LVLMs), yet its potential in real-time open-vocabulary object detectors, which also leverage large-scale vision-language datasets but smaller models, remains unexplored. This work investigates this domain, revealing intriguing insights. In the shallow layers, experts tend to cooperate with diverse peers to expand the search space. While in the deeper layers, fixed collaborative structures emerge, where each expert maintains 2-3 fixed partners and distinct expert combinations are specialized in processing sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17436","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/2507.17436/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":"2507.17436","created_at":"2026-07-05T11:42:07.591978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17436v1","created_at":"2026-07-05T11:42:07.591978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17436","created_at":"2026-07-05T11:42:07.591978+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WYPRYD2IAZC","created_at":"2026-07-05T11:42:07.591978+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WYPRYD2IAZCZ7FJ","created_at":"2026-07-05T11:42:07.591978+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WYPRYD2","created_at":"2026-07-05T11:42:07.591978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04908","citing_title":"HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts for Object Detection","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF","json":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF.json","graph_json":"https://pith.science/api/pith-number/2WYPRYD2IAZCZ7FJODIUOQ4RWF/graph.json","events_json":"https://pith.science/api/pith-number/2WYPRYD2IAZCZ7FJODIUOQ4RWF/events.json","paper":"https://pith.science/paper/2WYPRYD2"},"agent_actions":{"view_html":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF","download_json":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF.json","view_paper":"https://pith.science/paper/2WYPRYD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17436&json=true","fetch_graph":"https://pith.science/api/pith-number/2WYPRYD2IAZCZ7FJODIUOQ4RWF/graph.json","fetch_events":"https://pith.science/api/pith-number/2WYPRYD2IAZCZ7FJODIUOQ4RWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF/action/storage_attestation","attest_author":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF/action/author_attestation","sign_citation":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF/action/citation_signature","submit_replication":"https://pith.science/pith/2WYPRYD2IAZCZ7FJODIUOQ4RWF/action/replication_record"}},"created_at":"2026-07-05T11:42:07.591978+00:00","updated_at":"2026-07-05T11:42:07.591978+00:00"}