{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NYD5ZMD3AZB442OWHKOCD5CWQL","short_pith_number":"pith:NYD5ZMD3","schema_version":"1.0","canonical_sha256":"6e07dcb07b0643ce69d63a9c21f45682d9db91f085c9ebad5f2784d70215bf08","source":{"kind":"arxiv","id":"2605.30561","version":1},"attestation_state":"computed","paper":{"title":"VLM3: Vision Language Models Are Native 3D Learners","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Vikas Chandra, Yangyang Shi, Yunyang Xiong, Zechun Liu, Zhipeng Cai, Zhuang Liu","submitted_at":"2026-05-28T20:48:55Z","abstract_excerpt":"Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D understanding still largely relies on expert vision models with complex task-specific designs. The key argument this work wants to make is that VLMs are native 3D learners. Our in-depth large scale study shows that 1) focal length unification, 2) text-based pixel reference and 3) data mixture and scaling, are all you need for effective 3D learning. Model architecture changes, large models, heavy data augmentations, an"},"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":"2605.30561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T20:48:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a55a6ebc9027908514e83f2f1041c154626a08f32092dd9dd9169418b9f53689","abstract_canon_sha256":"095d247b1221f334a15207bf0efa358c7d1296e3321cefedc3b29c935a8c7e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:01.187915Z","signature_b64":"F2IyP4DGjghRgHkX65fe+TdJMz6GYBZKvVtNicnzqn+Zee6nHaj/i0PuoUDHUileKynzXv6JeCsceVGIdOfCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e07dcb07b0643ce69d63a9c21f45682d9db91f085c9ebad5f2784d70215bf08","last_reissued_at":"2026-06-01T01:03:01.186935Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:01.186935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM3: Vision Language Models Are Native 3D Learners","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Vikas Chandra, Yangyang Shi, Yunyang Xiong, Zechun Liu, Zhipeng Cai, Zhuang Liu","submitted_at":"2026-05-28T20:48:55Z","abstract_excerpt":"Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D understanding still largely relies on expert vision models with complex task-specific designs. The key argument this work wants to make is that VLMs are native 3D learners. Our in-depth large scale study shows that 1) focal length unification, 2) text-based pixel reference and 3) data mixture and scaling, are all you need for effective 3D learning. Model architecture changes, large models, heavy data augmentations, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30561","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/2605.30561/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":"2605.30561","created_at":"2026-06-01T01:03:01.187113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30561v1","created_at":"2026-06-01T01:03:01.187113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30561","created_at":"2026-06-01T01:03:01.187113+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYD5ZMD3AZB4","created_at":"2026-06-01T01:03:01.187113+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYD5ZMD3AZB442OW","created_at":"2026-06-01T01:03:01.187113+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYD5ZMD3","created_at":"2026-06-01T01:03:01.187113+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/NYD5ZMD3AZB442OWHKOCD5CWQL","json":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL.json","graph_json":"https://pith.science/api/pith-number/NYD5ZMD3AZB442OWHKOCD5CWQL/graph.json","events_json":"https://pith.science/api/pith-number/NYD5ZMD3AZB442OWHKOCD5CWQL/events.json","paper":"https://pith.science/paper/NYD5ZMD3"},"agent_actions":{"view_html":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL","download_json":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL.json","view_paper":"https://pith.science/paper/NYD5ZMD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30561&json=true","fetch_graph":"https://pith.science/api/pith-number/NYD5ZMD3AZB442OWHKOCD5CWQL/graph.json","fetch_events":"https://pith.science/api/pith-number/NYD5ZMD3AZB442OWHKOCD5CWQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL/action/storage_attestation","attest_author":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL/action/author_attestation","sign_citation":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL/action/citation_signature","submit_replication":"https://pith.science/pith/NYD5ZMD3AZB442OWHKOCD5CWQL/action/replication_record"}},"created_at":"2026-06-01T01:03:01.187113+00:00","updated_at":"2026-06-01T01:03:01.187113+00:00"}