{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MYYHQB2SQO5K23ZCRTUDSQSE32","short_pith_number":"pith:MYYHQB2S","schema_version":"1.0","canonical_sha256":"663078075283baad6f228ce8394244de84a207c850df7eb2320e04913eed36c1","source":{"kind":"arxiv","id":"2312.13286","version":2},"attestation_state":"computed","paper":{"title":"Generative Multimodal Models are In-Context Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Jingjing Liu, Qiying Yu, Quan Sun, Tiejun Huang, Xiaosong Zhang, Xinlong Wang, Yongming Rao, Yueze Wang, Yufeng Cui, Zhengxiong Luo","submitted_at":"2023-12-20T18:59:58Z","abstract_excerpt":"The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-context learning capabilities of large multimodal models can be significantly enhanced by effective scaling-up. We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences with a unified autoregressive objective. Emu2 exhibits strong multimodal in-context learning abilities, even emerging"},"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":"2312.13286","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T18:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"325310fdf6c424f7e5b2ffd38763da71ab1f79d1ff7ef35d281a8941e42892e0","abstract_canon_sha256":"9ef76dd4cd7ce5ca537e56dabf5e9791a8e29b8d7ba3c4c5c471108174c0319f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:45.633336Z","signature_b64":"LeC+kE3fzXOdFYjGDFAyZNg+yO1jjjQYWRvVWIu5dQCHxGKphL/GBiJy/ChfNWFvDFnyzlS9TWMzIgYGBNGMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"663078075283baad6f228ce8394244de84a207c850df7eb2320e04913eed36c1","last_reissued_at":"2026-07-05T08:16:45.632822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:45.632822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Multimodal Models are In-Context Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Jingjing Liu, Qiying Yu, Quan Sun, Tiejun Huang, Xiaosong Zhang, Xinlong Wang, Yongming Rao, Yueze Wang, Yufeng Cui, Zhengxiong Luo","submitted_at":"2023-12-20T18:59:58Z","abstract_excerpt":"The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-context learning capabilities of large multimodal models can be significantly enhanced by effective scaling-up. We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences with a unified autoregressive objective. Emu2 exhibits strong multimodal in-context learning abilities, even emerging"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13286","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/2312.13286/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":"2312.13286","created_at":"2026-07-05T08:16:45.632879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13286v2","created_at":"2026-07-05T08:16:45.632879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13286","created_at":"2026-07-05T08:16:45.632879+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYYHQB2SQO5K","created_at":"2026-07-05T08:16:45.632879+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYYHQB2SQO5K23ZC","created_at":"2026-07-05T08:16:45.632879+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYYHQB2S","created_at":"2026-07-05T08:16:45.632879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":245,"is_internal_anchor":false},{"citing_arxiv_id":"2403.18814","citing_title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09411","citing_title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10554","citing_title":"Grounding Everything in Tokens for Multimodal Large Language Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2311.03079","citing_title":"CogVLM: Visual Expert for Pretrained Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15809","citing_title":"MMaDA: Multimodal Large Diffusion Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16502","citing_title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2408.12528","citing_title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07726","citing_title":"PaliGemma: A versatile 3B VLM for transfer","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32","json":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32.json","graph_json":"https://pith.science/api/pith-number/MYYHQB2SQO5K23ZCRTUDSQSE32/graph.json","events_json":"https://pith.science/api/pith-number/MYYHQB2SQO5K23ZCRTUDSQSE32/events.json","paper":"https://pith.science/paper/MYYHQB2S"},"agent_actions":{"view_html":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32","download_json":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32.json","view_paper":"https://pith.science/paper/MYYHQB2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13286&json=true","fetch_graph":"https://pith.science/api/pith-number/MYYHQB2SQO5K23ZCRTUDSQSE32/graph.json","fetch_events":"https://pith.science/api/pith-number/MYYHQB2SQO5K23ZCRTUDSQSE32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32/action/storage_attestation","attest_author":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32/action/author_attestation","sign_citation":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32/action/citation_signature","submit_replication":"https://pith.science/pith/MYYHQB2SQO5K23ZCRTUDSQSE32/action/replication_record"}},"created_at":"2026-07-05T08:16:45.632879+00:00","updated_at":"2026-07-05T08:16:45.632879+00:00"}