{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LJHUW6AYODUNYUY3UBFIV6JLS7","short_pith_number":"pith:LJHUW6AY","schema_version":"1.0","canonical_sha256":"5a4f4b781870e8dc531ba04a8af92b97ce9163b929a16e03aaf471e3739edb0f","source":{"kind":"arxiv","id":"2311.12871","version":3},"attestation_state":"computed","paper":{"title":"An Embodied Generalist Agent in 3D World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LEO trains as a 3D embodied generalist agent through two-stage alignment on large vision-language and vision-language-action datasets.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Jiangyong Huang, Puhao Li, Qing Li, Silong Yong, Siyuan Huang, Song-Chun Zhu, Xiaojian Ma, Xiongkun Linghu, Yan Wang","submitted_at":"2023-11-18T01:21:38Z","abstract_excerpt":"Leveraging massive knowledge from large language models (LLMs), recent machine learning models show notable successes in general-purpose task solving in diverse domains such as computer vision and robotics. However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e.g., 3D grounding, embodied reasoning and acting. We argue these limitations significantly hinder current models from performing real-world tasks and approaching general intelligenc"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2311.12871","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-18T01:21:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d3f6a0a01ad1f88f36aa4d2acac57a9346d7c35c4738df676395e28791d80bc8","abstract_canon_sha256":"4f47ee0a5b4dedd7b27c6fe1061559319ed77d33695b15255171ac542dd21944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.839721Z","signature_b64":"ZpXWOEqX6grMWOJ2l+2qtq7Nb4Ly9BPmSudqWIy0jq61p92OePnffzC+oVNmfoGXZ1Wk6my3sTTs0GtM9TRQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a4f4b781870e8dc531ba04a8af92b97ce9163b929a16e03aaf471e3739edb0f","last_reissued_at":"2026-05-17T23:38:13.838991Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.838991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Embodied Generalist Agent in 3D World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LEO trains as a 3D embodied generalist agent through two-stage alignment on large vision-language and vision-language-action datasets.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Jiangyong Huang, Puhao Li, Qing Li, Silong Yong, Siyuan Huang, Song-Chun Zhu, Xiaojian Ma, Xiongkun Linghu, Yan Wang","submitted_at":"2023-11-18T01:21:38Z","abstract_excerpt":"Leveraging massive knowledge from large language models (LLMs), recent machine learning models show notable successes in general-purpose task solving in diverse domains such as computer vision and robotics. However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e.g., 3D grounding, embodied reasoning and acting. We argue these limitations significantly hinder current models from performing real-world tasks and approaching general intelligenc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through extensive experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, navigation and manipulation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The central claim assumes that the collected large-scale 3D VL and VLA datasets plus the two-stage training procedure are sufficient to produce generalist performance that transfers beyond the specific benchmarks shown.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LEO is an embodied generalist agent that performs 3D captioning, question answering, reasoning, navigation, and manipulation after 3D vision-language alignment followed by vision-language-action instruction tuning on large-scale object- and scene-level datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LEO trains as a 3D embodied generalist agent through two-stage alignment on large vision-language and vision-language-action datasets.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1ba28f9ab79b4d87813e61ea5758858db44d6e974a02ee779f4e777be0d75666"},"source":{"id":"2311.12871","kind":"arxiv","version":3},"verdict":{"id":"d9ad041c-600a-47ef-85dc-ec0ba0765a0a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T14:15:53.121198Z","strongest_claim":"Through extensive experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, navigation and manipulation.","one_line_summary":"LEO is an embodied generalist agent that performs 3D captioning, question answering, reasoning, navigation, and manipulation after 3D vision-language alignment followed by vision-language-action instruction tuning on large-scale object- and scene-level datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The central claim assumes that the collected large-scale 3D VL and VLA datasets plus the two-stage training procedure are sufficient to produce generalist performance that transfers beyond the specific benchmarks shown.","pith_extraction_headline":"LEO trains as a 3D embodied generalist agent through two-stage alignment on large vision-language and vision-language-action datasets."},"references":{"count":27,"sample":[{"doi":"","year":2022,"title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","work_id":"41dff74c-00b2-4c77-a674-9f86030c06c8","ref_index":1,"cited_arxiv_id":"2302.04023","is_internal_anchor":true},{"doi":"","year":2022,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","ref_index":2,"cited_arxiv_id":"2212.06817","is_internal_anchor":true},{"doi":"","year":2022,"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","ref_index":3,"cited_arxiv_id":"2210.11416","is_internal_anchor":true},{"doi":"","year":2022,"title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","work_id":"0fe2cfd8-d442-4ceb-b1a9-a465704f39b2","ref_index":4,"cited_arxiv_id":"2304.15010","is_internal_anchor":true},{"doi":"","year":2001,"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","ref_index":5,"cited_arxiv_id":"2001.08361","is_internal_anchor":true}],"resolved_work":27,"snapshot_sha256":"637ea65950bdb3b83fba8253b8026046cca6267d4912d88a95831e9a9b795c1e","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4a0c00bfe591c510c5d6f0e5e9394e6cb682f8a0b168a0fdf54511e583e49651"},"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":"2311.12871","created_at":"2026-05-17T23:38:13.839114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12871v3","created_at":"2026-05-17T23:38:13.839114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12871","created_at":"2026-05-17T23:38:13.839114+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJHUW6AYODUN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJHUW6AYODUNYUY3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJHUW6AY","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2510.20685","citing_title":"C-NAV: Towards Self-Evolving Continual Object Navigation in Open World","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2511.15279","citing_title":"Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16567","citing_title":"POMA-3D: The Point Map Way to 3D Scene Understanding","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":248,"is_internal_anchor":true},{"citing_arxiv_id":"2505.23747","citing_title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2602.00937","citing_title":"CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2602.10698","citing_title":"AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2603.08096","citing_title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2603.17980","citing_title":"Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27437","citing_title":"SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2504.13958","citing_title":"ToolRL: Reward is All Tool Learning Needs","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01907","citing_title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2403.09631","citing_title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27699","citing_title":"Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10485","citing_title":"VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2506.21539","citing_title":"WorldVLA: Towards Autoregressive Action World Model","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05126","citing_title":"ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08340","citing_title":"PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7","json":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7.json","graph_json":"https://pith.science/api/pith-number/LJHUW6AYODUNYUY3UBFIV6JLS7/graph.json","events_json":"https://pith.science/api/pith-number/LJHUW6AYODUNYUY3UBFIV6JLS7/events.json","paper":"https://pith.science/paper/LJHUW6AY"},"agent_actions":{"view_html":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7","download_json":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7.json","view_paper":"https://pith.science/paper/LJHUW6AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12871&json=true","fetch_graph":"https://pith.science/api/pith-number/LJHUW6AYODUNYUY3UBFIV6JLS7/graph.json","fetch_events":"https://pith.science/api/pith-number/LJHUW6AYODUNYUY3UBFIV6JLS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7/action/storage_attestation","attest_author":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7/action/author_attestation","sign_citation":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7/action/citation_signature","submit_replication":"https://pith.science/pith/LJHUW6AYODUNYUY3UBFIV6JLS7/action/replication_record"}},"created_at":"2026-05-17T23:38:13.839114+00:00","updated_at":"2026-05-17T23:38:13.839114+00:00"}