{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J4Z633WN4DCLY4PFTTAWIOKNUT","short_pith_number":"pith:J4Z633WN","schema_version":"1.0","canonical_sha256":"4f33edeecde0c4bc71e59cc164394da4fedab3ce934fef50a866881a2459ef17","source":{"kind":"arxiv","id":"2507.20110","version":1},"attestation_state":"computed","paper":{"title":"NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Lianlei Shan, Shiyu Liu","submitted_at":"2025-07-27T03:11:08Z","abstract_excerpt":"Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse, large-scale point clouds due to slow feature extraction and limited representation accuracy. To address these challenges, we propose NeuroVoxel-LM, a novel framework that integrates Neural Radiance Fields (NeRF) with dynamic resolution voxelization and lightweight meta-embedding. Specifically, we introduce a Dynamic Resolution Multiscale Voxelization (DR-MS"},"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":"2507.20110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T03:11:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b79efcfdedc80b7eb34e4c3c324b4ef28a9f2823f1bc3257a5f3c80525f7bdd8","abstract_canon_sha256":"6883dfda5750769d2c92e3dbe260adef31167398c898b7341b7327a8aaac43e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:13.403618Z","signature_b64":"SgXJHaMzehHIsp7WhjIMkD8pVrRoHnUBh14mqBjkW8pWiMEMvSu42qz57h2E2R2xn0T7Puswzo84x3tRiUE3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f33edeecde0c4bc71e59cc164394da4fedab3ce934fef50a866881a2459ef17","last_reissued_at":"2026-07-05T11:44:13.403060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:13.403060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Lianlei Shan, Shiyu Liu","submitted_at":"2025-07-27T03:11:08Z","abstract_excerpt":"Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse, large-scale point clouds due to slow feature extraction and limited representation accuracy. To address these challenges, we propose NeuroVoxel-LM, a novel framework that integrates Neural Radiance Fields (NeRF) with dynamic resolution voxelization and lightweight meta-embedding. Specifically, we introduce a Dynamic Resolution Multiscale Voxelization (DR-MS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20110","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/2507.20110/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":"2507.20110","created_at":"2026-07-05T11:44:13.403123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20110v1","created_at":"2026-07-05T11:44:13.403123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20110","created_at":"2026-07-05T11:44:13.403123+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4Z633WN4DCL","created_at":"2026-07-05T11:44:13.403123+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4Z633WN4DCLY4PF","created_at":"2026-07-05T11:44:13.403123+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4Z633WN","created_at":"2026-07-05T11:44:13.403123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT","json":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT.json","graph_json":"https://pith.science/api/pith-number/J4Z633WN4DCLY4PFTTAWIOKNUT/graph.json","events_json":"https://pith.science/api/pith-number/J4Z633WN4DCLY4PFTTAWIOKNUT/events.json","paper":"https://pith.science/paper/J4Z633WN"},"agent_actions":{"view_html":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT","download_json":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT.json","view_paper":"https://pith.science/paper/J4Z633WN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20110&json=true","fetch_graph":"https://pith.science/api/pith-number/J4Z633WN4DCLY4PFTTAWIOKNUT/graph.json","fetch_events":"https://pith.science/api/pith-number/J4Z633WN4DCLY4PFTTAWIOKNUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT/action/storage_attestation","attest_author":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT/action/author_attestation","sign_citation":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT/action/citation_signature","submit_replication":"https://pith.science/pith/J4Z633WN4DCLY4PFTTAWIOKNUT/action/replication_record"}},"created_at":"2026-07-05T11:44:13.403123+00:00","updated_at":"2026-07-05T11:44:13.403123+00:00"}