{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CUPYEUJQ5H5BGLL2C7BR2EAQWO","short_pith_number":"pith:CUPYEUJQ","schema_version":"1.0","canonical_sha256":"151f825130e9fa132d7a17c31d1010b3b9967cb880e38b9d5e114ab78c646ef6","source":{"kind":"arxiv","id":"2509.00039","version":1},"attestation_state":"computed","paper":{"title":"AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanguang Yang, Hansheng Zeng, Haoyan Xu, Junhao Dong, Yingli Tian, Yuqi Li, Zeyu Dong, Zhengtao Yao, Zhulin An","submitted_at":"2025-08-23T04:52:20Z","abstract_excerpt":"The success of large-scale visual language pretraining (VLP) models has driven widespread adoption of image-text retrieval tasks. However, their deployment on mobile devices remains limited due to large model sizes and computational complexity. We propose Adaptive Multi-Modal Multi-Teacher Knowledge Distillation (AMMKD), a novel framework that integrates multi-modal feature fusion, multi-teacher distillation, and adaptive optimization to deliver lightweight yet effective retrieval models. Specifically, our method begins with a feature fusion network that extracts and merges discriminative feat"},"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":"2509.00039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-23T04:52:20Z","cross_cats_sorted":[],"title_canon_sha256":"0cb7d689a4df210191f7c42a99543a3c9b43a7458ec2bb5293b8b2cfcf04cf8e","abstract_canon_sha256":"e480f98ff75f6bd0ef5cb9e6326b681c44e8663d02e4090e0f3e89324547bb84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:08.328621Z","signature_b64":"lyJP6L9Ho+4SKqQWUUgucTXByrNpogxPBuMeFVB1v+RPZ3aknwls7utfaNxdRVudxrAUD0Ze4R5HeY0MhlagCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"151f825130e9fa132d7a17c31d1010b3b9967cb880e38b9d5e114ab78c646ef6","last_reissued_at":"2026-07-05T12:02:08.328024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:08.328024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanguang Yang, Hansheng Zeng, Haoyan Xu, Junhao Dong, Yingli Tian, Yuqi Li, Zeyu Dong, Zhengtao Yao, Zhulin An","submitted_at":"2025-08-23T04:52:20Z","abstract_excerpt":"The success of large-scale visual language pretraining (VLP) models has driven widespread adoption of image-text retrieval tasks. However, their deployment on mobile devices remains limited due to large model sizes and computational complexity. We propose Adaptive Multi-Modal Multi-Teacher Knowledge Distillation (AMMKD), a novel framework that integrates multi-modal feature fusion, multi-teacher distillation, and adaptive optimization to deliver lightweight yet effective retrieval models. Specifically, our method begins with a feature fusion network that extracts and merges discriminative feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00039","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/2509.00039/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":"2509.00039","created_at":"2026-07-05T12:02:08.328113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00039v1","created_at":"2026-07-05T12:02:08.328113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00039","created_at":"2026-07-05T12:02:08.328113+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUPYEUJQ5H5B","created_at":"2026-07-05T12:02:08.328113+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUPYEUJQ5H5BGLL2","created_at":"2026-07-05T12:02:08.328113+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUPYEUJQ","created_at":"2026-07-05T12:02:08.328113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25758","citing_title":"Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22394","citing_title":"Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09253","citing_title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00305","citing_title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09253","citing_title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00305","citing_title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO","json":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO.json","graph_json":"https://pith.science/api/pith-number/CUPYEUJQ5H5BGLL2C7BR2EAQWO/graph.json","events_json":"https://pith.science/api/pith-number/CUPYEUJQ5H5BGLL2C7BR2EAQWO/events.json","paper":"https://pith.science/paper/CUPYEUJQ"},"agent_actions":{"view_html":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO","download_json":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO.json","view_paper":"https://pith.science/paper/CUPYEUJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00039&json=true","fetch_graph":"https://pith.science/api/pith-number/CUPYEUJQ5H5BGLL2C7BR2EAQWO/graph.json","fetch_events":"https://pith.science/api/pith-number/CUPYEUJQ5H5BGLL2C7BR2EAQWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO/action/storage_attestation","attest_author":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO/action/author_attestation","sign_citation":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO/action/citation_signature","submit_replication":"https://pith.science/pith/CUPYEUJQ5H5BGLL2C7BR2EAQWO/action/replication_record"}},"created_at":"2026-07-05T12:02:08.328113+00:00","updated_at":"2026-07-05T12:02:08.328113+00:00"}