{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CD6XH4E6G6QLWZBEB3B6WKKAVL","short_pith_number":"pith:CD6XH4E6","schema_version":"1.0","canonical_sha256":"10fd73f09e37a0bb64240ec3eb2940aad40800a9b7cbe22569098dababad6435","source":{"kind":"arxiv","id":"2404.07989","version":3},"attestation_state":"computed","paper":{"title":"Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bin Zhao, Dong Wang, Hongsheng Li, Jiaming Liu, Peng Gao, Ray Zhang, Shanghang Zhang, Xuelong Li, Yiwen Tang, Zhigang Wang, Zoey Guo","submitted_at":"2024-04-11T17:59:45Z","abstract_excerpt":"Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D domains. However, such 2D-to-3D approaches are still limited, due to the potential loss of spatial geometries and high computation cost. More importantly, their frameworks are mainly designed for 2D models, lacking a general any-to-3D paradigm. In this paper, we introduce Any2Point, a parameter-efficient method to empower any-modality large models (v"},"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":"2404.07989","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-11T17:59:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"e2a52bbd234d030874ca99da50056f1dd24ffcc1df4451ade4ebf460cadb73b4","abstract_canon_sha256":"b93e68f4688cef3eef8a7ab657f8f3888eb7de11f791d544f1ca05c44edd7650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:04.837470Z","signature_b64":"Xb9DEblIXngH7Tk5RX0TAjSrPRq392sTsMwKUP9sb1FqOIYnfszaOze1B3znm2UOKuO9s915doMlhV7rN7tHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10fd73f09e37a0bb64240ec3eb2940aad40800a9b7cbe22569098dababad6435","last_reissued_at":"2026-07-05T09:23:04.836991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:04.836991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bin Zhao, Dong Wang, Hongsheng Li, Jiaming Liu, Peng Gao, Ray Zhang, Shanghang Zhang, Xuelong Li, Yiwen Tang, Zhigang Wang, Zoey Guo","submitted_at":"2024-04-11T17:59:45Z","abstract_excerpt":"Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D domains. However, such 2D-to-3D approaches are still limited, due to the potential loss of spatial geometries and high computation cost. More importantly, their frameworks are mainly designed for 2D models, lacking a general any-to-3D paradigm. In this paper, we introduce Any2Point, a parameter-efficient method to empower any-modality large models (v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07989","kind":"arxiv","version":3},"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/2404.07989/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":"2404.07989","created_at":"2026-07-05T09:23:04.837049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07989v3","created_at":"2026-07-05T09:23:04.837049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07989","created_at":"2026-07-05T09:23:04.837049+00:00"},{"alias_kind":"pith_short_12","alias_value":"CD6XH4E6G6QL","created_at":"2026-07-05T09:23:04.837049+00:00"},{"alias_kind":"pith_short_16","alias_value":"CD6XH4E6G6QLWZBE","created_at":"2026-07-05T09:23:04.837049+00:00"},{"alias_kind":"pith_short_8","alias_value":"CD6XH4E6","created_at":"2026-07-05T09:23:04.837049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14837","citing_title":"ObjVariantEnsemble: Advancing Point Cloud LLM Evaluation in Challenging Scenes with Subtly Distinguished Objects","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL","json":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL.json","graph_json":"https://pith.science/api/pith-number/CD6XH4E6G6QLWZBEB3B6WKKAVL/graph.json","events_json":"https://pith.science/api/pith-number/CD6XH4E6G6QLWZBEB3B6WKKAVL/events.json","paper":"https://pith.science/paper/CD6XH4E6"},"agent_actions":{"view_html":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL","download_json":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL.json","view_paper":"https://pith.science/paper/CD6XH4E6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07989&json=true","fetch_graph":"https://pith.science/api/pith-number/CD6XH4E6G6QLWZBEB3B6WKKAVL/graph.json","fetch_events":"https://pith.science/api/pith-number/CD6XH4E6G6QLWZBEB3B6WKKAVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL/action/storage_attestation","attest_author":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL/action/author_attestation","sign_citation":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL/action/citation_signature","submit_replication":"https://pith.science/pith/CD6XH4E6G6QLWZBEB3B6WKKAVL/action/replication_record"}},"created_at":"2026-07-05T09:23:04.837049+00:00","updated_at":"2026-07-05T09:23:04.837049+00:00"}