{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F2X2DNYHXPLT5ZEVZQTKKJFMAX","short_pith_number":"pith:F2X2DNYH","schema_version":"1.0","canonical_sha256":"2eafa1b707bbd73ee495cc26a524ac05f070c886938e037ef6ef39d50ad871da","source":{"kind":"arxiv","id":"2409.14096","version":1},"attestation_state":"computed","paper":{"title":"VLM-Vac: Enhancing Smart Vacuums through VLM Knowledge Distillation and Language-Guided Experience Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Florian Walter, Michael Krawez, Reihaneh Mirjalili, Wolfram Burgard","submitted_at":"2024-09-21T10:32:21Z","abstract_excerpt":"In this paper, we propose VLM-Vac, a novel framework designed to enhance the autonomy of smart robot vacuum cleaners. Our approach integrates the zero-shot object detection capabilities of a Vision-Language Model (VLM) with a Knowledge Distillation (KD) strategy. By leveraging the VLM, the robot can categorize objects into actionable classes -- either to avoid or to suck -- across diverse backgrounds. However, frequently querying the VLM is computationally expensive and impractical for real-world deployment. To address this issue, we implement a KD process that gradually transfers the essentia"},"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":"2409.14096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-21T10:32:21Z","cross_cats_sorted":[],"title_canon_sha256":"85a913482d698756f2556b54a5c2b3ac034ef4c943b05fd07a57ce77edda136a","abstract_canon_sha256":"628075bb244dafd222a2e4acaed943b5034a2fbd86225fca3c1710bb376bb079"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:11.630527Z","signature_b64":"XCTqDDqAfz1s3BSjsUfYY4LZ/D+7HPujMh1jqN7hhOD08P4gSldwdVCMy4Kyv7fv9pz49SuQntNrEGvqZ2mnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eafa1b707bbd73ee495cc26a524ac05f070c886938e037ef6ef39d50ad871da","last_reissued_at":"2026-07-05T09:10:11.630112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:11.630112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-Vac: Enhancing Smart Vacuums through VLM Knowledge Distillation and Language-Guided Experience Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Florian Walter, Michael Krawez, Reihaneh Mirjalili, Wolfram Burgard","submitted_at":"2024-09-21T10:32:21Z","abstract_excerpt":"In this paper, we propose VLM-Vac, a novel framework designed to enhance the autonomy of smart robot vacuum cleaners. Our approach integrates the zero-shot object detection capabilities of a Vision-Language Model (VLM) with a Knowledge Distillation (KD) strategy. By leveraging the VLM, the robot can categorize objects into actionable classes -- either to avoid or to suck -- across diverse backgrounds. However, frequently querying the VLM is computationally expensive and impractical for real-world deployment. To address this issue, we implement a KD process that gradually transfers the essentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14096","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/2409.14096/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":"2409.14096","created_at":"2026-07-05T09:10:11.630170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14096v1","created_at":"2026-07-05T09:10:11.630170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14096","created_at":"2026-07-05T09:10:11.630170+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2X2DNYHXPLT","created_at":"2026-07-05T09:10:11.630170+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2X2DNYHXPLT5ZEV","created_at":"2026-07-05T09:10:11.630170+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2X2DNYH","created_at":"2026-07-05T09:10:11.630170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11334","citing_title":"CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX","json":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX.json","graph_json":"https://pith.science/api/pith-number/F2X2DNYHXPLT5ZEVZQTKKJFMAX/graph.json","events_json":"https://pith.science/api/pith-number/F2X2DNYHXPLT5ZEVZQTKKJFMAX/events.json","paper":"https://pith.science/paper/F2X2DNYH"},"agent_actions":{"view_html":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX","download_json":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX.json","view_paper":"https://pith.science/paper/F2X2DNYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14096&json=true","fetch_graph":"https://pith.science/api/pith-number/F2X2DNYHXPLT5ZEVZQTKKJFMAX/graph.json","fetch_events":"https://pith.science/api/pith-number/F2X2DNYHXPLT5ZEVZQTKKJFMAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX/action/storage_attestation","attest_author":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX/action/author_attestation","sign_citation":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX/action/citation_signature","submit_replication":"https://pith.science/pith/F2X2DNYHXPLT5ZEVZQTKKJFMAX/action/replication_record"}},"created_at":"2026-07-05T09:10:11.630170+00:00","updated_at":"2026-07-05T09:10:11.630170+00:00"}