{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LHM7VL374JQOODY47IQAH2OLPB","short_pith_number":"pith:LHM7VL37","schema_version":"1.0","canonical_sha256":"59d9faaf7fe260e70f1cfa2003e9cb784b5e521f5d6b614bdb399b3fc8ace761","source":{"kind":"arxiv","id":"2411.05755","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Antonio Loquercio, Dylan Goetting, Himanshu Gaurav Singh","submitted_at":"2024-11-08T18:16:58Z","abstract_excerpt":"We present VLMnav, an embodied framework to transform a Vision-Language Model (VLM) into an end-to-end navigation policy. In contrast to prior work, we do not rely on a separation between perception, planning, and control; instead, we use a VLM to directly select actions in one step. Surprisingly, we find that a VLM can be used as an end-to-end policy zero-shot, i.e., without any fine-tuning or exposure to navigation data. This makes our approach open-ended and generalizable to any downstream navigation task. We run an extensive study to evaluate the performance of our approach in comparison t"},"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":"2411.05755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T18:16:58Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"5c6cfc868f5874a585e690c510f2eed6c30ecfda3ef31dd95e16b3a422ff327a","abstract_canon_sha256":"55b0bc8daf0f34dfc0f7d03bdfa2dd1285f68d9028cccc06287649ba28707e46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:06.251374Z","signature_b64":"9e4VE7YwSjGclPEHgn8fKE6TpDSCYKcQTNOSSkcwoEP+CEs8lnxIbcy1ZFGh1YVWK3zd9pfseoUGADKz7gqFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59d9faaf7fe260e70f1cfa2003e9cb784b5e521f5d6b614bdb399b3fc8ace761","last_reissued_at":"2026-07-05T09:33:06.250792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:06.250792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Antonio Loquercio, Dylan Goetting, Himanshu Gaurav Singh","submitted_at":"2024-11-08T18:16:58Z","abstract_excerpt":"We present VLMnav, an embodied framework to transform a Vision-Language Model (VLM) into an end-to-end navigation policy. In contrast to prior work, we do not rely on a separation between perception, planning, and control; instead, we use a VLM to directly select actions in one step. Surprisingly, we find that a VLM can be used as an end-to-end policy zero-shot, i.e., without any fine-tuning or exposure to navigation data. This makes our approach open-ended and generalizable to any downstream navigation task. We run an extensive study to evaluate the performance of our approach in comparison t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05755","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/2411.05755/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":"2411.05755","created_at":"2026-07-05T09:33:06.250856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05755v1","created_at":"2026-07-05T09:33:06.250856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05755","created_at":"2026-07-05T09:33:06.250856+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHM7VL374JQO","created_at":"2026-07-05T09:33:06.250856+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHM7VL374JQOODY4","created_at":"2026-07-05T09:33:06.250856+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHM7VL37","created_at":"2026-07-05T09:33:06.250856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02417","citing_title":"LIME: Learning Intent-aware Camera Motion from Egocentric Video","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03509","citing_title":"EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05377","citing_title":"OpenFrontier: General Navigation with Visual-Language Grounded Frontiers","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17435","citing_title":"ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26788","citing_title":"ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27955","citing_title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08509","citing_title":"Visually-grounded Humanoid Agents","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB","json":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB.json","graph_json":"https://pith.science/api/pith-number/LHM7VL374JQOODY47IQAH2OLPB/graph.json","events_json":"https://pith.science/api/pith-number/LHM7VL374JQOODY47IQAH2OLPB/events.json","paper":"https://pith.science/paper/LHM7VL37"},"agent_actions":{"view_html":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB","download_json":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB.json","view_paper":"https://pith.science/paper/LHM7VL37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05755&json=true","fetch_graph":"https://pith.science/api/pith-number/LHM7VL374JQOODY47IQAH2OLPB/graph.json","fetch_events":"https://pith.science/api/pith-number/LHM7VL374JQOODY47IQAH2OLPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/action/storage_attestation","attest_author":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/action/author_attestation","sign_citation":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/action/citation_signature","submit_replication":"https://pith.science/pith/LHM7VL374JQOODY47IQAH2OLPB/action/replication_record"}},"created_at":"2026-07-05T09:33:06.250856+00:00","updated_at":"2026-07-05T09:33:06.250856+00:00"}