{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QGYNBJY2MFV6HQJDCY2EI2TC25","short_pith_number":"pith:QGYNBJY2","schema_version":"1.0","canonical_sha256":"81b0d0a71a616be3c1231634446a62d764799f9585059aae50724d866fe831bf","source":{"kind":"arxiv","id":"2307.10802","version":1},"attestation_state":"computed","paper":{"title":"Meta-Transformer: A Unified Framework for Multimodal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Kaipeng Zhang, Kaixiong Gong, Wanli Ouyang, Xiangyu Yue, Yiyuan Zhang, Yu Qiao","submitted_at":"2023-07-20T12:10:29Z","abstract_excerpt":"Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities ($\\textit{e.g.}$ natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a $\\textbf{frozen}$ encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input"},"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":"2307.10802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T12:10:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"4f6198f57f2568f824855782b0d9de01c8f99cb3a15fd61df877d974232aad06","abstract_canon_sha256":"1971519404a6c2858dbc6a1ccb161b1918cfc86777f94ba40e9646417faf2c9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:10.277386Z","signature_b64":"OhPBhSk9PAQEc2gPXzRrg/S2y/W3HUSowi6bSd/dJeL6yaKQR5fx0yhSnRYJu0tViIL0JxaWPKzfhoeJI8YrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b0d0a71a616be3c1231634446a62d764799f9585059aae50724d866fe831bf","last_reissued_at":"2026-07-05T06:33:10.276962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:10.276962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Transformer: A Unified Framework for Multimodal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Kaipeng Zhang, Kaixiong Gong, Wanli Ouyang, Xiangyu Yue, Yiyuan Zhang, Yu Qiao","submitted_at":"2023-07-20T12:10:29Z","abstract_excerpt":"Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities ($\\textit{e.g.}$ natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a $\\textbf{frozen}$ encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10802","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/2307.10802/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":"2307.10802","created_at":"2026-07-05T06:33:10.277019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10802v1","created_at":"2026-07-05T06:33:10.277019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10802","created_at":"2026-07-05T06:33:10.277019+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGYNBJY2MFV6","created_at":"2026-07-05T06:33:10.277019+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGYNBJY2MFV6HQJD","created_at":"2026-07-05T06:33:10.277019+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGYNBJY2","created_at":"2026-07-05T06:33:10.277019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28809","citing_title":"AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16639","citing_title":"MedMIX: Modality-Internal Expert Fusion for Multimodal Medical Diagnosis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18257","citing_title":"CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18169","citing_title":"PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05704","citing_title":"QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25","json":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25.json","graph_json":"https://pith.science/api/pith-number/QGYNBJY2MFV6HQJDCY2EI2TC25/graph.json","events_json":"https://pith.science/api/pith-number/QGYNBJY2MFV6HQJDCY2EI2TC25/events.json","paper":"https://pith.science/paper/QGYNBJY2"},"agent_actions":{"view_html":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25","download_json":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25.json","view_paper":"https://pith.science/paper/QGYNBJY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10802&json=true","fetch_graph":"https://pith.science/api/pith-number/QGYNBJY2MFV6HQJDCY2EI2TC25/graph.json","fetch_events":"https://pith.science/api/pith-number/QGYNBJY2MFV6HQJDCY2EI2TC25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25/action/storage_attestation","attest_author":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25/action/author_attestation","sign_citation":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25/action/citation_signature","submit_replication":"https://pith.science/pith/QGYNBJY2MFV6HQJDCY2EI2TC25/action/replication_record"}},"created_at":"2026-07-05T06:33:10.277019+00:00","updated_at":"2026-07-05T06:33:10.277019+00:00"}