{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RTF5O4LCFFQDA5PFOSEZKFV62N","short_pith_number":"pith:RTF5O4LC","schema_version":"1.0","canonical_sha256":"8ccbd7716229603075e574899516bed346dcd4ce75232f758e640c4a7748c80a","source":{"kind":"arxiv","id":"2410.13860","version":1},"attestation_state":"computed","paper":{"title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiangmiao Pang, Runsen Xu, Tai Wang, Yilun Chen, Zhiwei Huang","submitted_at":"2024-10-17T17:59:55Z","abstract_excerpt":"3D visual grounding is crucial for robots, requiring integration of natural language and 3D scene understanding. Traditional methods depending on supervised learning with 3D point clouds are limited by scarce datasets. Recently zero-shot methods leveraging LLMs have been proposed to address the data issue. While effective, these methods only use object-centric information, limiting their ability to handle complex queries. In this work, we present VLM-Grounder, a novel framework using vision-language models (VLMs) for zero-shot 3D visual grounding based solely on 2D images. VLM-Grounder dynamic"},"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":"2410.13860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:59:55Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"836e17e7210b8283594b1b40c01be8324dcab16d4223b263e88be3cbcb21b19c","abstract_canon_sha256":"322ba48e08d1b93f7edb53a9709d3ca4ef8f3c7db9d6b07c0f22c58a94cb20a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:06.736125Z","signature_b64":"Ym5wmRWycA8KOBhQW23TKd+PgY+jyK30H3s9trOpxzk8JESsn2Is4pohWSfb91ZLx2ebbasWmDzpH4xfSSpkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ccbd7716229603075e574899516bed346dcd4ce75232f758e640c4a7748c80a","last_reissued_at":"2026-07-05T09:22:06.735650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:06.735650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiangmiao Pang, Runsen Xu, Tai Wang, Yilun Chen, Zhiwei Huang","submitted_at":"2024-10-17T17:59:55Z","abstract_excerpt":"3D visual grounding is crucial for robots, requiring integration of natural language and 3D scene understanding. Traditional methods depending on supervised learning with 3D point clouds are limited by scarce datasets. Recently zero-shot methods leveraging LLMs have been proposed to address the data issue. While effective, these methods only use object-centric information, limiting their ability to handle complex queries. In this work, we present VLM-Grounder, a novel framework using vision-language models (VLMs) for zero-shot 3D visual grounding based solely on 2D images. VLM-Grounder dynamic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13860","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/2410.13860/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":"2410.13860","created_at":"2026-07-05T09:22:06.735707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13860v1","created_at":"2026-07-05T09:22:06.735707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13860","created_at":"2026-07-05T09:22:06.735707+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTF5O4LCFFQD","created_at":"2026-07-05T09:22:06.735707+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTF5O4LCFFQDA5PF","created_at":"2026-07-05T09:22:06.735707+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTF5O4LC","created_at":"2026-07-05T09:22:06.735707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19340","citing_title":"ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30231","citing_title":"Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21788","citing_title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19710","citing_title":"PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02786","citing_title":"QuadAgent: A Responsive Agent System for Vision-Language Guided Quadrotor Agile Flight","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26261","citing_title":"Multiple Consistent 2D-3D Mappings for Robust Zero-Shot 3D Visual Grounding","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N","json":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N.json","graph_json":"https://pith.science/api/pith-number/RTF5O4LCFFQDA5PFOSEZKFV62N/graph.json","events_json":"https://pith.science/api/pith-number/RTF5O4LCFFQDA5PFOSEZKFV62N/events.json","paper":"https://pith.science/paper/RTF5O4LC"},"agent_actions":{"view_html":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N","download_json":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N.json","view_paper":"https://pith.science/paper/RTF5O4LC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13860&json=true","fetch_graph":"https://pith.science/api/pith-number/RTF5O4LCFFQDA5PFOSEZKFV62N/graph.json","fetch_events":"https://pith.science/api/pith-number/RTF5O4LCFFQDA5PFOSEZKFV62N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N/action/storage_attestation","attest_author":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N/action/author_attestation","sign_citation":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N/action/citation_signature","submit_replication":"https://pith.science/pith/RTF5O4LCFFQDA5PFOSEZKFV62N/action/replication_record"}},"created_at":"2026-07-05T09:22:06.735707+00:00","updated_at":"2026-07-05T09:22:06.735707+00:00"}