{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G55CEGWQZSJLGXRRGFQ4LDZ2WO","short_pith_number":"pith:G55CEGWQ","schema_version":"1.0","canonical_sha256":"377a221ad0cc92b35e313161c58f3ab3addb50bec4763c45bf7214cc739f50c9","source":{"kind":"arxiv","id":"2506.01853","version":1},"attestation_state":"computed","paper":{"title":"ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junliang Ye, Jun Zhu, Ruowen Zhao, Shenghao Xie, Zhengyi Wang","submitted_at":"2025-06-02T16:40:50Z","abstract_excerpt":"Recently, the powerful text-to-image capabilities of ChatGPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities remain confined to images and text. Yet beyond images, the ability to understand and generate 3D content is equally crucial. To address this gap, we propose ShapeLLM-Omni-a native 3D large language model capable of understanding and generating 3D assets and text in any sequence. First, we train a 3D vector-quantized variational autoencoder (VQVAE), which maps 3D objects into a discrete latent space to achieve efficien"},"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":"2506.01853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T16:40:50Z","cross_cats_sorted":[],"title_canon_sha256":"faad098424af0f4776d9c3517abf8a1f8b738176d3fdc1a258dc709a8146c38d","abstract_canon_sha256":"f0b70b252323ea3fff953f6d437e2e9a0463cbedaa10c8590a9b03df88fb10bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:20.431621Z","signature_b64":"MMcZF9qEj097rrIoytbAFH5Vq+vuHHoL/xC6OmdomGdPN07tzrKk8ElqIGneCmHBGJJac8KjJEOHRvDABWLkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"377a221ad0cc92b35e313161c58f3ab3addb50bec4763c45bf7214cc739f50c9","last_reissued_at":"2026-07-05T11:14:20.431181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:20.431181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junliang Ye, Jun Zhu, Ruowen Zhao, Shenghao Xie, Zhengyi Wang","submitted_at":"2025-06-02T16:40:50Z","abstract_excerpt":"Recently, the powerful text-to-image capabilities of ChatGPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities remain confined to images and text. Yet beyond images, the ability to understand and generate 3D content is equally crucial. To address this gap, we propose ShapeLLM-Omni-a native 3D large language model capable of understanding and generating 3D assets and text in any sequence. First, we train a 3D vector-quantized variational autoencoder (VQVAE), which maps 3D objects into a discrete latent space to achieve efficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01853","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/2506.01853/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":"2506.01853","created_at":"2026-07-05T11:14:20.431233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01853v1","created_at":"2026-07-05T11:14:20.431233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01853","created_at":"2026-07-05T11:14:20.431233+00:00"},{"alias_kind":"pith_short_12","alias_value":"G55CEGWQZSJL","created_at":"2026-07-05T11:14:20.431233+00:00"},{"alias_kind":"pith_short_16","alias_value":"G55CEGWQZSJLGXRR","created_at":"2026-07-05T11:14:20.431233+00:00"},{"alias_kind":"pith_short_8","alias_value":"G55CEGWQ","created_at":"2026-07-05T11:14:20.431233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06565","citing_title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30673","citing_title":"PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28548","citing_title":"GEM: Generative Supervision Helps Embodied Intelligence","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21572","citing_title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16745","citing_title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13030","citing_title":"Motus: A Unified Latent Action World Model","ref_index":54,"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":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":206,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO","json":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO.json","graph_json":"https://pith.science/api/pith-number/G55CEGWQZSJLGXRRGFQ4LDZ2WO/graph.json","events_json":"https://pith.science/api/pith-number/G55CEGWQZSJLGXRRGFQ4LDZ2WO/events.json","paper":"https://pith.science/paper/G55CEGWQ"},"agent_actions":{"view_html":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO","download_json":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO.json","view_paper":"https://pith.science/paper/G55CEGWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01853&json=true","fetch_graph":"https://pith.science/api/pith-number/G55CEGWQZSJLGXRRGFQ4LDZ2WO/graph.json","fetch_events":"https://pith.science/api/pith-number/G55CEGWQZSJLGXRRGFQ4LDZ2WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO/action/storage_attestation","attest_author":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO/action/author_attestation","sign_citation":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO/action/citation_signature","submit_replication":"https://pith.science/pith/G55CEGWQZSJLGXRRGFQ4LDZ2WO/action/replication_record"}},"created_at":"2026-07-05T11:14:20.431233+00:00","updated_at":"2026-07-05T11:14:20.431233+00:00"}