{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LZAGGJODNSLDREKRL3HYBW5T4D","short_pith_number":"pith:LZAGGJOD","schema_version":"1.0","canonical_sha256":"5e406325c36c963891515ecf80dbb3e0c52bb774d5e733d3497f101dbb425489","source":{"kind":"arxiv","id":"2312.03700","version":2},"attestation_state":"computed","paper":{"title":"OneLLM: One Framework to Align All Modalities with Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaming Han, Jiaqi Wang, Kaipeng Zhang, Kaixiong Gong, Peng Gao, Xiangyu Yue, Yiyuan Zhang, Yu Qiao","submitted_at":"2023-12-06T18:59:19Z","abstract_excerpt":"Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and are limited to common modalities. In this paper, we present OneLLM, an MLLM that aligns eight modalities to language using a unified framework. We achieve this through a unified multimodal encoder and a progressive multimodal alignment pipeline. In detail, we first train an image projection module to connect a vision encoder with LLM. Then, we build a unive"},"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":"2312.03700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:59:19Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"614e0d573a49adf8956b3daf60915fab2304e8932db5476dc92d76c6397cad28","abstract_canon_sha256":"95bc10c360683a1bf768ce4f996504a6bc35a16c46d59086a0033ec75f80f867"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:57.128263Z","signature_b64":"xXEoUSj5l5q9ct9SBYoZ1k1datmRIA5WR7XUuOmybriRJTHWSFRAqQv2D5RZKNSR6zFD+FOSNDEhVYdMeqJEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e406325c36c963891515ecf80dbb3e0c52bb774d5e733d3497f101dbb425489","last_reissued_at":"2026-07-05T09:58:57.127764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:57.127764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OneLLM: One Framework to Align All Modalities with Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaming Han, Jiaqi Wang, Kaipeng Zhang, Kaixiong Gong, Peng Gao, Xiangyu Yue, Yiyuan Zhang, Yu Qiao","submitted_at":"2023-12-06T18:59:19Z","abstract_excerpt":"Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and are limited to common modalities. In this paper, we present OneLLM, an MLLM that aligns eight modalities to language using a unified framework. We achieve this through a unified multimodal encoder and a progressive multimodal alignment pipeline. In detail, we first train an image projection module to connect a vision encoder with LLM. Then, we build a unive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03700","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/2312.03700/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":"2312.03700","created_at":"2026-07-05T09:58:57.127829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03700v2","created_at":"2026-07-05T09:58:57.127829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03700","created_at":"2026-07-05T09:58:57.127829+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZAGGJODNSLD","created_at":"2026-07-05T09:58:57.127829+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZAGGJODNSLDREKR","created_at":"2026-07-05T09:58:57.127829+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZAGGJOD","created_at":"2026-07-05T09:58:57.127829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29591","citing_title":"Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19950","citing_title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D","json":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D.json","graph_json":"https://pith.science/api/pith-number/LZAGGJODNSLDREKRL3HYBW5T4D/graph.json","events_json":"https://pith.science/api/pith-number/LZAGGJODNSLDREKRL3HYBW5T4D/events.json","paper":"https://pith.science/paper/LZAGGJOD"},"agent_actions":{"view_html":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D","download_json":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D.json","view_paper":"https://pith.science/paper/LZAGGJOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03700&json=true","fetch_graph":"https://pith.science/api/pith-number/LZAGGJODNSLDREKRL3HYBW5T4D/graph.json","fetch_events":"https://pith.science/api/pith-number/LZAGGJODNSLDREKRL3HYBW5T4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D/action/storage_attestation","attest_author":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D/action/author_attestation","sign_citation":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D/action/citation_signature","submit_replication":"https://pith.science/pith/LZAGGJODNSLDREKRL3HYBW5T4D/action/replication_record"}},"created_at":"2026-07-05T09:58:57.127829+00:00","updated_at":"2026-07-05T09:58:57.127829+00:00"}