{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XBBYNHH2DEZA7BDQWX2EC6XXJX","short_pith_number":"pith:XBBYNHH2","schema_version":"1.0","canonical_sha256":"b843869cfa19320f8470b5f4417af74de28a2329d41febaa97cd6bfd98468928","source":{"kind":"arxiv","id":"2310.02992","version":3},"attestation_state":"computed","paper":{"title":"Kosmos-G: Generating Images in Context with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Li Dong, Shaohan Huang, Wenhu Chen, Xichen Pan, Zhiliang Peng","submitted_at":"2023-10-04T17:28:44Z","abstract_excerpt":"Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of \"image as a foreign language in image generation.\" This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLI"},"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":"2310.02992","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-04T17:28:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1c7b8dcd8668b3a097d44f49b7a7d5a41a6343b1d65773748a6a73625177ed5e","abstract_canon_sha256":"f37fb21951b0abda0e91d1909a750ec09e67b568affc5faa127ee7431ca24a2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:14.232591Z","signature_b64":"bBstJV6pxYY/s4P9RycDJ9/OLMRvTILdNJVf+S5uRbjmaLymKLejdDRbsetpIKB02cMRYluE6vnXHGr/R63dBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b843869cfa19320f8470b5f4417af74de28a2329d41febaa97cd6bfd98468928","last_reissued_at":"2026-07-05T08:12:14.232123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:14.232123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kosmos-G: Generating Images in Context with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Li Dong, Shaohan Huang, Wenhu Chen, Xichen Pan, Zhiliang Peng","submitted_at":"2023-10-04T17:28:44Z","abstract_excerpt":"Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of \"image as a foreign language in image generation.\" This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02992","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/2310.02992/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":"2310.02992","created_at":"2026-07-05T08:12:14.232188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02992v3","created_at":"2026-07-05T08:12:14.232188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02992","created_at":"2026-07-05T08:12:14.232188+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBBYNHH2DEZA","created_at":"2026-07-05T08:12:14.232188+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBBYNHH2DEZA7BDQ","created_at":"2026-07-05T08:12:14.232188+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBBYNHH2","created_at":"2026-07-05T08:12:14.232188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.16702","citing_title":"Animalbooth: multimodal feature enhancement for animal subject personalization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12305","citing_title":"Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18562","citing_title":"AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation","ref_index":192,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX","json":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX.json","graph_json":"https://pith.science/api/pith-number/XBBYNHH2DEZA7BDQWX2EC6XXJX/graph.json","events_json":"https://pith.science/api/pith-number/XBBYNHH2DEZA7BDQWX2EC6XXJX/events.json","paper":"https://pith.science/paper/XBBYNHH2"},"agent_actions":{"view_html":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX","download_json":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX.json","view_paper":"https://pith.science/paper/XBBYNHH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02992&json=true","fetch_graph":"https://pith.science/api/pith-number/XBBYNHH2DEZA7BDQWX2EC6XXJX/graph.json","fetch_events":"https://pith.science/api/pith-number/XBBYNHH2DEZA7BDQWX2EC6XXJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX/action/storage_attestation","attest_author":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX/action/author_attestation","sign_citation":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX/action/citation_signature","submit_replication":"https://pith.science/pith/XBBYNHH2DEZA7BDQWX2EC6XXJX/action/replication_record"}},"created_at":"2026-07-05T08:12:14.232188+00:00","updated_at":"2026-07-05T08:12:14.232188+00:00"}