{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XLPKTF4WLNJ3YPOYOQKKH4UR6V","short_pith_number":"pith:XLPKTF4W","schema_version":"1.0","canonical_sha256":"badea997965b53bc3dd87414a3f291f5525e2295988d2a3ed90107f8be279c19","source":{"kind":"arxiv","id":"2211.12402","version":2},"attestation_state":"computed","paper":{"title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hang Li, Jiawei Wang, Jipeng Zhang, Wangchunshu Zhou, Xinsong Zhang, Yan Zeng","submitted_at":"2022-11-22T16:48:01Z","abstract_excerpt":"Vision language pre-training aims to learn alignments between vision and language from a large amount of data. Most existing methods only learn image-text alignments. Some others utilize pre-trained object detectors to leverage vision language alignments at the object level. In this paper, we propose to learn multi-grained vision language alignments by a unified pre-training framework that learns multi-grained aligning and multi-grained localization simultaneously. Based on it, we present X$^2$-VLM, an all-in-one model with a flexible modular architecture, in which we further unify image-text "},"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":"2211.12402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T16:48:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"39be0f5add8f32a57727f0d07c716ba10f00e259c629e356a3ee4ff06d3930ad","abstract_canon_sha256":"78a9f88056bbe0b1cb2c802b7154e7892be3c957f4a4220a5ac236baee7eb138"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:46.427119Z","signature_b64":"vKugHxgXyykMTKNmWWbwKy3d8gwnA3V9bJ/JKUs/eQslzq3066H2XAqFRJ5ra7SulxMFKZPtn81wb3cNyVugCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"badea997965b53bc3dd87414a3f291f5525e2295988d2a3ed90107f8be279c19","last_reissued_at":"2026-07-05T06:35:46.425728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:46.425728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hang Li, Jiawei Wang, Jipeng Zhang, Wangchunshu Zhou, Xinsong Zhang, Yan Zeng","submitted_at":"2022-11-22T16:48:01Z","abstract_excerpt":"Vision language pre-training aims to learn alignments between vision and language from a large amount of data. Most existing methods only learn image-text alignments. Some others utilize pre-trained object detectors to leverage vision language alignments at the object level. In this paper, we propose to learn multi-grained vision language alignments by a unified pre-training framework that learns multi-grained aligning and multi-grained localization simultaneously. Based on it, we present X$^2$-VLM, an all-in-one model with a flexible modular architecture, in which we further unify image-text "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12402","kind":"arxiv","version":2},"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/2211.12402/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":"2211.12402","created_at":"2026-07-05T06:35:46.425858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12402v2","created_at":"2026-07-05T06:35:46.425858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12402","created_at":"2026-07-05T06:35:46.425858+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLPKTF4WLNJ3","created_at":"2026-07-05T06:35:46.425858+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLPKTF4WLNJ3YPOY","created_at":"2026-07-05T06:35:46.425858+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLPKTF4W","created_at":"2026-07-05T06:35:46.425858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2311.01378","citing_title":"Vision-Language Foundation Models as Effective Robot Imitators","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V","json":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V.json","graph_json":"https://pith.science/api/pith-number/XLPKTF4WLNJ3YPOYOQKKH4UR6V/graph.json","events_json":"https://pith.science/api/pith-number/XLPKTF4WLNJ3YPOYOQKKH4UR6V/events.json","paper":"https://pith.science/paper/XLPKTF4W"},"agent_actions":{"view_html":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V","download_json":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V.json","view_paper":"https://pith.science/paper/XLPKTF4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12402&json=true","fetch_graph":"https://pith.science/api/pith-number/XLPKTF4WLNJ3YPOYOQKKH4UR6V/graph.json","fetch_events":"https://pith.science/api/pith-number/XLPKTF4WLNJ3YPOYOQKKH4UR6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V/action/storage_attestation","attest_author":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V/action/author_attestation","sign_citation":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V/action/citation_signature","submit_replication":"https://pith.science/pith/XLPKTF4WLNJ3YPOYOQKKH4UR6V/action/replication_record"}},"created_at":"2026-07-05T06:35:46.425858+00:00","updated_at":"2026-07-05T06:35:46.425858+00:00"}