{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4VOX56ID2WBQQW6DNLK5B4AZAF","short_pith_number":"pith:4VOX56ID","schema_version":"1.0","canonical_sha256":"e55d7ef903d583085bc36ad5d0f019014e10441288c7491e79b0af6342afc9b0","source":{"kind":"arxiv","id":"2409.18800","version":1},"attestation_state":"computed","paper":{"title":"MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Junyou Zhu, Qi Wu, Siqi Zhang, Xingjian He, Yanyuan Qiao","submitted_at":"2024-09-27T14:54:54Z","abstract_excerpt":"In recent years, Embodied Artificial Intelligence (Embodied AI) has advanced rapidly, yet the increasing size of models conflicts with the limited computational capabilities of Embodied AI platforms. To address this challenge, we aim to achieve both high model performance and practical deployability. Specifically, we focus on Vision-and-Language Navigation (VLN), a core task in Embodied AI. This paper introduces a two-stage knowledge distillation framework, producing a student model, MiniVLN, and showcasing the significant potential of distillation techniques in developing lightweight models. "},"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":"2409.18800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-27T14:54:54Z","cross_cats_sorted":[],"title_canon_sha256":"12f2732290f07d41036461e634a61ba40ca756b7669fe726a2dc48eec9e271b1","abstract_canon_sha256":"162238563128f25d6295aabdd30cf8098a6076c00aa06d9ff461ec0c96cd2bdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:48.539402Z","signature_b64":"R1NQNCFiaP9ELbBvW+otVMyK8iVMPPjiCHW4tGDEXxsdO92VEV1mIYhZPolix/pS5t07cn062p4hb8T4F04zCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e55d7ef903d583085bc36ad5d0f019014e10441288c7491e79b0af6342afc9b0","last_reissued_at":"2026-07-05T09:12:48.538968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:48.538968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liu, Junyou Zhu, Qi Wu, Siqi Zhang, Xingjian He, Yanyuan Qiao","submitted_at":"2024-09-27T14:54:54Z","abstract_excerpt":"In recent years, Embodied Artificial Intelligence (Embodied AI) has advanced rapidly, yet the increasing size of models conflicts with the limited computational capabilities of Embodied AI platforms. To address this challenge, we aim to achieve both high model performance and practical deployability. Specifically, we focus on Vision-and-Language Navigation (VLN), a core task in Embodied AI. This paper introduces a two-stage knowledge distillation framework, producing a student model, MiniVLN, and showcasing the significant potential of distillation techniques in developing lightweight models. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18800","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/2409.18800/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":"2409.18800","created_at":"2026-07-05T09:12:48.539024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18800v1","created_at":"2026-07-05T09:12:48.539024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18800","created_at":"2026-07-05T09:12:48.539024+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VOX56ID2WBQ","created_at":"2026-07-05T09:12:48.539024+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VOX56ID2WBQQW6D","created_at":"2026-07-05T09:12:48.539024+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VOX56ID","created_at":"2026-07-05T09:12:48.539024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.07080","citing_title":"VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF","json":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF.json","graph_json":"https://pith.science/api/pith-number/4VOX56ID2WBQQW6DNLK5B4AZAF/graph.json","events_json":"https://pith.science/api/pith-number/4VOX56ID2WBQQW6DNLK5B4AZAF/events.json","paper":"https://pith.science/paper/4VOX56ID"},"agent_actions":{"view_html":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF","download_json":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF.json","view_paper":"https://pith.science/paper/4VOX56ID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18800&json=true","fetch_graph":"https://pith.science/api/pith-number/4VOX56ID2WBQQW6DNLK5B4AZAF/graph.json","fetch_events":"https://pith.science/api/pith-number/4VOX56ID2WBQQW6DNLK5B4AZAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF/action/storage_attestation","attest_author":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF/action/author_attestation","sign_citation":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF/action/citation_signature","submit_replication":"https://pith.science/pith/4VOX56ID2WBQQW6DNLK5B4AZAF/action/replication_record"}},"created_at":"2026-07-05T09:12:48.539024+00:00","updated_at":"2026-07-05T09:12:48.539024+00:00"}