{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JC6ZRCGTU4R4H3JNCF36DLWYQN","short_pith_number":"pith:JC6ZRCGT","schema_version":"1.0","canonical_sha256":"48bd9888d3a723c3ed2d1177e1aed8835e51119f416bd6f86ce89db5335994e1","source":{"kind":"arxiv","id":"2405.10370","version":2},"attestation_state":"computed","paper":{"title":"Grounded 3D-LLM with Referent Tokens","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Haifeng Huang, Jiangmiao Pang, Ruiyuan Lyu, Runsen Xu, Shuai Yang, Tai Wang, Yilun Chen","submitted_at":"2024-05-16T18:03:41Z","abstract_excerpt":"Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal models (3D LMMs) to consolidate various 3D vision tasks within a unified generative framework. The model uses scene referent tokens as special noun phrases to reference 3D scenes, enabling it to handle sequences that interleave 3D and textual data. Per-task instruction-following templates are employed to ensure natural and diversity in translating 3D vision ta"},"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":"2405.10370","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T18:03:41Z","cross_cats_sorted":[],"title_canon_sha256":"91a5d4a68f16ca737b3fe08773e817e82bbed835ee469461f2446b7e115cb4c0","abstract_canon_sha256":"ef1054067ea70719d9905f84f2c1aa81f17ee35dc47b006bf89464751c024a25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:40.878224Z","signature_b64":"Wkkh+WpC/VXFKuRb8B68t7Zv37G4XDCZxmygKepvUBFOfrjbXIVXHhglLgupVLrM9BxSh2lYfO3T4oiSgu2sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48bd9888d3a723c3ed2d1177e1aed8835e51119f416bd6f86ce89db5335994e1","last_reissued_at":"2026-07-05T09:36:40.877755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:40.877755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounded 3D-LLM with Referent Tokens","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Haifeng Huang, Jiangmiao Pang, Ruiyuan Lyu, Runsen Xu, Shuai Yang, Tai Wang, Yilun Chen","submitted_at":"2024-05-16T18:03:41Z","abstract_excerpt":"Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal models (3D LMMs) to consolidate various 3D vision tasks within a unified generative framework. The model uses scene referent tokens as special noun phrases to reference 3D scenes, enabling it to handle sequences that interleave 3D and textual data. Per-task instruction-following templates are employed to ensure natural and diversity in translating 3D vision ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10370","kind":"arxiv","version":2},"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/2405.10370/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":"2405.10370","created_at":"2026-07-05T09:36:40.877809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10370v2","created_at":"2026-07-05T09:36:40.877809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10370","created_at":"2026-07-05T09:36:40.877809+00:00"},{"alias_kind":"pith_short_12","alias_value":"JC6ZRCGTU4R4","created_at":"2026-07-05T09:36:40.877809+00:00"},{"alias_kind":"pith_short_16","alias_value":"JC6ZRCGTU4R4H3JN","created_at":"2026-07-05T09:36:40.877809+00:00"},{"alias_kind":"pith_short_8","alias_value":"JC6ZRCGT","created_at":"2026-07-05T09:36:40.877809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06534","citing_title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19828","citing_title":"3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06485","citing_title":"PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03100","citing_title":"Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01215","citing_title":"Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01215","citing_title":"Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28490","citing_title":"SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06239","citing_title":"Open-Architecture End-to-End System for Real-World Autonomous Robot Navigation","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23747","citing_title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05199","citing_title":"DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23365","citing_title":"SpatialMosaic: A Multiview VLM Dataset for Partial Visibility","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23747","citing_title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17980","citing_title":"Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03296","citing_title":"3D-IDE: 3D Implicit Depth Emergent","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03318","citing_title":"EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02689","citing_title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01365","citing_title":"VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05695","citing_title":"Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21160","citing_title":"Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN","json":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN.json","graph_json":"https://pith.science/api/pith-number/JC6ZRCGTU4R4H3JNCF36DLWYQN/graph.json","events_json":"https://pith.science/api/pith-number/JC6ZRCGTU4R4H3JNCF36DLWYQN/events.json","paper":"https://pith.science/paper/JC6ZRCGT"},"agent_actions":{"view_html":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN","download_json":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN.json","view_paper":"https://pith.science/paper/JC6ZRCGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10370&json=true","fetch_graph":"https://pith.science/api/pith-number/JC6ZRCGTU4R4H3JNCF36DLWYQN/graph.json","fetch_events":"https://pith.science/api/pith-number/JC6ZRCGTU4R4H3JNCF36DLWYQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN/action/storage_attestation","attest_author":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN/action/author_attestation","sign_citation":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN/action/citation_signature","submit_replication":"https://pith.science/pith/JC6ZRCGTU4R4H3JNCF36DLWYQN/action/replication_record"}},"created_at":"2026-07-05T09:36:40.877809+00:00","updated_at":"2026-07-05T09:36:40.877809+00:00"}