{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SPRQZIL2RBPPIKIAETVMSO5VC3","short_pith_number":"pith:SPRQZIL2","schema_version":"1.0","canonical_sha256":"93e30ca17a885ef4290024eac93bb516ceec5fe1e4f926b5386fc838b83c1796","source":{"kind":"arxiv","id":"2411.14402","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alaaeldin El-Nouby, Alexander T Toshev, David Haldimann, Enrico Fini, Joshua M. Susskind, Louis B\\'ethune, Marcin Eichner, Michal Klein, Moin Nabi, Mustafa Shukor, Philipp Dufter, Sai Aitharaju, Victor Guilherme Turrisi da Costa, Xiujun Li, Yinfei Yang, Zhe Gan","submitted_at":"2024-11-21T18:31:25Z","abstract_excerpt":"We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this paper, we present AIMV2, a family of generalist vision encoders characterized by a straightforward pre-training process, scalability, and remarkable performance across a range of downstream tasks. This is achieved by pairing the vision encoder with a multimodal decoder that autoregressively generates raw image patches and text tokens. Our encoders excel not o"},"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":"2411.14402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:31:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d770e26372ffb7eb535d9c78aa50b7155ab915f423e3ac9a0434c9afb837825","abstract_canon_sha256":"0cb1e9ee7ab50cfe5a0be3781918d20a8ea790ab2a5692dedc0967d99d5649b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:46.447225Z","signature_b64":"EGwOsVFpN8yneKV8+ayis2QznAg1+ZQs9JrqRA0olUcv7Xi+aNacYqyVTsj3l9X8WPSN7tdONVmxMuvAfnkVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93e30ca17a885ef4290024eac93bb516ceec5fe1e4f926b5386fc838b83c1796","last_reissued_at":"2026-07-05T09:38:46.446706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:46.446706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alaaeldin El-Nouby, Alexander T Toshev, David Haldimann, Enrico Fini, Joshua M. Susskind, Louis B\\'ethune, Marcin Eichner, Michal Klein, Moin Nabi, Mustafa Shukor, Philipp Dufter, Sai Aitharaju, Victor Guilherme Turrisi da Costa, Xiujun Li, Yinfei Yang, Zhe Gan","submitted_at":"2024-11-21T18:31:25Z","abstract_excerpt":"We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this paper, we present AIMV2, a family of generalist vision encoders characterized by a straightforward pre-training process, scalability, and remarkable performance across a range of downstream tasks. This is achieved by pairing the vision encoder with a multimodal decoder that autoregressively generates raw image patches and text tokens. Our encoders excel not o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14402","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/2411.14402/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":"2411.14402","created_at":"2026-07-05T09:38:46.446767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14402v1","created_at":"2026-07-05T09:38:46.446767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14402","created_at":"2026-07-05T09:38:46.446767+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPRQZIL2RBPP","created_at":"2026-07-05T09:38:46.446767+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPRQZIL2RBPPIKIA","created_at":"2026-07-05T09:38:46.446767+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPRQZIL2","created_at":"2026-07-05T09:38:46.446767+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.02597","citing_title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09082","citing_title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09985","citing_title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.14786","citing_title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17376","citing_title":"Towards Generalizable Deepfake Image Detection with Vision Transformers","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3","json":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3.json","graph_json":"https://pith.science/api/pith-number/SPRQZIL2RBPPIKIAETVMSO5VC3/graph.json","events_json":"https://pith.science/api/pith-number/SPRQZIL2RBPPIKIAETVMSO5VC3/events.json","paper":"https://pith.science/paper/SPRQZIL2"},"agent_actions":{"view_html":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3","download_json":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3.json","view_paper":"https://pith.science/paper/SPRQZIL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14402&json=true","fetch_graph":"https://pith.science/api/pith-number/SPRQZIL2RBPPIKIAETVMSO5VC3/graph.json","fetch_events":"https://pith.science/api/pith-number/SPRQZIL2RBPPIKIAETVMSO5VC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/action/storage_attestation","attest_author":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/action/author_attestation","sign_citation":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/action/citation_signature","submit_replication":"https://pith.science/pith/SPRQZIL2RBPPIKIAETVMSO5VC3/action/replication_record"}},"created_at":"2026-07-05T09:38:46.446767+00:00","updated_at":"2026-07-05T09:38:46.446767+00:00"}