{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C3TCS67ZEQMFH3KJYWY2UTA3U3","short_pith_number":"pith:C3TCS67Z","schema_version":"1.0","canonical_sha256":"16e6297bf9241853ed49c5b1aa4c1ba6c626b0af70cfe5ea045547eed8c97307","source":{"kind":"arxiv","id":"2505.17726","version":3},"attestation_state":"computed","paper":{"title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daejin Jo, Donghoon Lee, Donghwan Chi, Hyomin Kim, Jongmin Kim, Junyeob Baek, Sungjin Ahn, Sungwoong Kim, Yongjin Kim, Yoonjin Oh","submitted_at":"2025-05-23T10:43:45Z","abstract_excerpt":"Recently, multimodal large language models (MLLMs) have emerged as a key approach in achieving artificial general intelligence. In particular, vision-language MLLMs have been developed to generate not only text but also visual outputs from multimodal inputs. This advancement requires efficient image tokens that LLMs can process effectively both in input and output. However, existing image tokenization methods for MLLMs typically capture only global abstract concepts or uniformly segmented image patches, restricting MLLMs' capability to effectively understand or generate detailed visual content"},"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":"2505.17726","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T10:43:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d1b63c9c959228ec94c930189e60a80f5ce6fe70f6d55ee8a961cad0f8aebcab","abstract_canon_sha256":"2ce34951eeb6fd716a56096413d9aee93d40e5ed9aeaf8a20b0505c86f6fb56b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:54.357091Z","signature_b64":"DupK35UMM3evOSYoEDO/j7StzMaffpdSui9Jc4tsXuafpqp0BV7IOe5TLtLCgRZhmsUB45NaJTLlsYfwacldCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16e6297bf9241853ed49c5b1aa4c1ba6c626b0af70cfe5ea045547eed8c97307","last_reissued_at":"2026-05-20T01:04:54.356188Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:54.356188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daejin Jo, Donghoon Lee, Donghwan Chi, Hyomin Kim, Jongmin Kim, Junyeob Baek, Sungjin Ahn, Sungwoong Kim, Yongjin Kim, Yoonjin Oh","submitted_at":"2025-05-23T10:43:45Z","abstract_excerpt":"Recently, multimodal large language models (MLLMs) have emerged as a key approach in achieving artificial general intelligence. In particular, vision-language MLLMs have been developed to generate not only text but also visual outputs from multimodal inputs. This advancement requires efficient image tokens that LLMs can process effectively both in input and output. However, existing image tokenization methods for MLLMs typically capture only global abstract concepts or uniformly segmented image patches, restricting MLLMs' capability to effectively understand or generate detailed visual content"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17726","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/2505.17726/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":"2505.17726","created_at":"2026-05-20T01:04:54.356306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17726v3","created_at":"2026-05-20T01:04:54.356306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17726","created_at":"2026-05-20T01:04:54.356306+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3TCS67ZEQMF","created_at":"2026-05-20T01:04:54.356306+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3TCS67ZEQMFH3KJ","created_at":"2026-05-20T01:04:54.356306+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3TCS67Z","created_at":"2026-05-20T01:04:54.356306+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17954","citing_title":"A More Word-like Image Tokenization for MLLMs","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3","json":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3.json","graph_json":"https://pith.science/api/pith-number/C3TCS67ZEQMFH3KJYWY2UTA3U3/graph.json","events_json":"https://pith.science/api/pith-number/C3TCS67ZEQMFH3KJYWY2UTA3U3/events.json","paper":"https://pith.science/paper/C3TCS67Z"},"agent_actions":{"view_html":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3","download_json":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3.json","view_paper":"https://pith.science/paper/C3TCS67Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17726&json=true","fetch_graph":"https://pith.science/api/pith-number/C3TCS67ZEQMFH3KJYWY2UTA3U3/graph.json","fetch_events":"https://pith.science/api/pith-number/C3TCS67ZEQMFH3KJYWY2UTA3U3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3/action/storage_attestation","attest_author":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3/action/author_attestation","sign_citation":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3/action/citation_signature","submit_replication":"https://pith.science/pith/C3TCS67ZEQMFH3KJYWY2UTA3U3/action/replication_record"}},"created_at":"2026-05-20T01:04:54.356306+00:00","updated_at":"2026-05-20T01:04:54.356306+00:00"}