{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ALR2RBT3OAGXWTDIYFFKMLT4RK","short_pith_number":"pith:ALR2RBT3","schema_version":"1.0","canonical_sha256":"02e3a8867b700d7b4c68c14aa62e7c8a92c42bfb2dc2d0c91bd3ceef89a6a262","source":{"kind":"arxiv","id":"2507.08505","version":2},"attestation_state":"computed","paper":{"title":"Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pablo Robin Guerrero, Sanidhya Kashyap, Yueyang Pan","submitted_at":"2025-07-11T11:30:57Z","abstract_excerpt":"Vision-Language Models (VLMs) offer promising capabilities for mobile devices, but their deployment faces significant challenges due to computational limitations and energy inefficiency, especially for real-time applications. This study provides a comprehensive survey of deployment frameworks for VLMs on mobile devices, evaluating llama.cpp, MLC-Imp, and mllm in the context of running LLaVA-1.5 7B, MobileVLM-3B, and Imp-v1.5 3B as representative workloads on a OnePlus 13R. Each deployment framework was evaluated on the OnePlus 13R while running VLMs, with measurements covering CPU, GPU, and NP"},"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":"2507.08505","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T11:30:57Z","cross_cats_sorted":[],"title_canon_sha256":"e10981ba0dde5119f589c90c76c85acbbb614b6700b9ca3ee00697e08d695dae","abstract_canon_sha256":"dcc431545c3b9ac75a599b459fe9bbb6b8c8516aa95bc03accc99d1fc6f04ce4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:35.669483Z","signature_b64":"xIFiHzNHenwBHYf84DTNCKngIYPph4t1AeH7InSwyd9eyPn6kkdIsJZgRZ022ZP0g1PVtNgAByuhGR14lpmtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02e3a8867b700d7b4c68c14aa62e7c8a92c42bfb2dc2d0c91bd3ceef89a6a262","last_reissued_at":"2026-07-05T11:36:35.668886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:35.668886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pablo Robin Guerrero, Sanidhya Kashyap, Yueyang Pan","submitted_at":"2025-07-11T11:30:57Z","abstract_excerpt":"Vision-Language Models (VLMs) offer promising capabilities for mobile devices, but their deployment faces significant challenges due to computational limitations and energy inefficiency, especially for real-time applications. This study provides a comprehensive survey of deployment frameworks for VLMs on mobile devices, evaluating llama.cpp, MLC-Imp, and mllm in the context of running LLaVA-1.5 7B, MobileVLM-3B, and Imp-v1.5 3B as representative workloads on a OnePlus 13R. Each deployment framework was evaluated on the OnePlus 13R while running VLMs, with measurements covering CPU, GPU, and NP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08505","kind":"arxiv","version":2},"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/2507.08505/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":"2507.08505","created_at":"2026-07-05T11:36:35.668953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08505v2","created_at":"2026-07-05T11:36:35.668953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08505","created_at":"2026-07-05T11:36:35.668953+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALR2RBT3OAGX","created_at":"2026-07-05T11:36:35.668953+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALR2RBT3OAGXWTDI","created_at":"2026-07-05T11:36:35.668953+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALR2RBT3","created_at":"2026-07-05T11:36:35.668953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.21531","citing_title":"On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26508","citing_title":"Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK","json":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK.json","graph_json":"https://pith.science/api/pith-number/ALR2RBT3OAGXWTDIYFFKMLT4RK/graph.json","events_json":"https://pith.science/api/pith-number/ALR2RBT3OAGXWTDIYFFKMLT4RK/events.json","paper":"https://pith.science/paper/ALR2RBT3"},"agent_actions":{"view_html":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK","download_json":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK.json","view_paper":"https://pith.science/paper/ALR2RBT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08505&json=true","fetch_graph":"https://pith.science/api/pith-number/ALR2RBT3OAGXWTDIYFFKMLT4RK/graph.json","fetch_events":"https://pith.science/api/pith-number/ALR2RBT3OAGXWTDIYFFKMLT4RK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK/action/storage_attestation","attest_author":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK/action/author_attestation","sign_citation":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK/action/citation_signature","submit_replication":"https://pith.science/pith/ALR2RBT3OAGXWTDIYFFKMLT4RK/action/replication_record"}},"created_at":"2026-07-05T11:36:35.668953+00:00","updated_at":"2026-07-05T11:36:35.668953+00:00"}