{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NL7A2FBFWDBPQXVIKCZO5PPA6A","short_pith_number":"pith:NL7A2FBF","schema_version":"1.0","canonical_sha256":"6afe0d1425b0c2f85ea850b2eebde0f034994c1c8d3ab2c18757b4889e2c7a2f","source":{"kind":"arxiv","id":"2504.09724","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Efficient Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anuradha Ravi, Emon Dey, Gaurav Shinde, Milind Rampure, Nirmalya Roy, Shadman Sakib","submitted_at":"2025-04-13T21:12:24Z","abstract_excerpt":"Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs"},"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":"2504.09724","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T21:12:24Z","cross_cats_sorted":[],"title_canon_sha256":"11abb33544857b50fe53056827a90109c3c88e2c1c8b19b193b754e8d5744ae9","abstract_canon_sha256":"66c8f29c453612087b04dfa7b6906be7e6d42de97265570b91805b45169f5f97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:22.331642Z","signature_b64":"cqSt7vIRKF/RhCxaBhtvZQVYS8jUMZ2y4jvhfcSsYHg7npjsiyhdFziqvwSDUJMKO8V/Kim0HYLmATxlrLiOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6afe0d1425b0c2f85ea850b2eebde0f034994c1c8d3ab2c18757b4889e2c7a2f","last_reissued_at":"2026-07-05T11:30:22.331128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:22.331128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Efficient Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anuradha Ravi, Emon Dey, Gaurav Shinde, Milind Rampure, Nirmalya Roy, Shadman Sakib","submitted_at":"2025-04-13T21:12:24Z","abstract_excerpt":"Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09724","kind":"arxiv","version":3},"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/2504.09724/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":"2504.09724","created_at":"2026-07-05T11:30:22.331192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09724v3","created_at":"2026-07-05T11:30:22.331192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09724","created_at":"2026-07-05T11:30:22.331192+00:00"},{"alias_kind":"pith_short_12","alias_value":"NL7A2FBFWDBP","created_at":"2026-07-05T11:30:22.331192+00:00"},{"alias_kind":"pith_short_16","alias_value":"NL7A2FBFWDBPQXVI","created_at":"2026-07-05T11:30:22.331192+00:00"},{"alias_kind":"pith_short_8","alias_value":"NL7A2FBF","created_at":"2026-07-05T11:30:22.331192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05546","citing_title":"Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05210","citing_title":"Integration of Object Detection and Small VLMs for Construction Safety Hazard Identification","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A","json":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A.json","graph_json":"https://pith.science/api/pith-number/NL7A2FBFWDBPQXVIKCZO5PPA6A/graph.json","events_json":"https://pith.science/api/pith-number/NL7A2FBFWDBPQXVIKCZO5PPA6A/events.json","paper":"https://pith.science/paper/NL7A2FBF"},"agent_actions":{"view_html":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A","download_json":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A.json","view_paper":"https://pith.science/paper/NL7A2FBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09724&json=true","fetch_graph":"https://pith.science/api/pith-number/NL7A2FBFWDBPQXVIKCZO5PPA6A/graph.json","fetch_events":"https://pith.science/api/pith-number/NL7A2FBFWDBPQXVIKCZO5PPA6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A/action/storage_attestation","attest_author":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A/action/author_attestation","sign_citation":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A/action/citation_signature","submit_replication":"https://pith.science/pith/NL7A2FBFWDBPQXVIKCZO5PPA6A/action/replication_record"}},"created_at":"2026-07-05T11:30:22.331192+00:00","updated_at":"2026-07-05T11:30:22.331192+00:00"}