{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZQ2HYQJJJTSBIXGPFTWINYARAW","short_pith_number":"pith:ZQ2HYQJJ","schema_version":"1.0","canonical_sha256":"cc347c41294ce4145ccf2cec86e01105b77ffc3a89e132f9a07db240d3b47938","source":{"kind":"arxiv","id":"2407.06438","version":3},"attestation_state":"computed","paper":{"title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Peng, Heng Ji, Xingyao Wang, Yangyi Chen","submitted_at":"2024-07-08T22:40:15Z","abstract_excerpt":"We present SOLO, a single transformer for Scalable visiOn-Language mOdeling. Current large vision-language models (LVLMs) such as LLaVA mostly employ heterogeneous architectures that connect pre-trained visual encoders with large language models (LLMs) to facilitate visual recognition and complex reasoning. Although achieving remarkable performance with relatively lightweight training, we identify four primary scalability limitations: (1) The visual capacity is constrained by pre-trained visual encoders, which are typically an order of magnitude smaller than LLMs. (2) The heterogeneous archite"},"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":"2407.06438","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T22:40:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3dce8376d2af5df0d1f178d48941e54f93ab27d0cda121525c38c7d08da6983c","abstract_canon_sha256":"47bfd7e0f9ca14f7b1f96a7eaaf9aa5422cdfeca8f0f8584f13af2779e8c5be6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:07.575301Z","signature_b64":"u+y3rmdXOfrvgpYtfeE8yYIJrBlRtFiJOvLQyY5AceRGq20YPj+cDQ8jVfrBQEjfqDb5DVjKrh8OqKqcA7clCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc347c41294ce4145ccf2cec86e01105b77ffc3a89e132f9a07db240d3b47938","last_reissued_at":"2026-07-05T09:49:07.574782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:07.574782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Peng, Heng Ji, Xingyao Wang, Yangyi Chen","submitted_at":"2024-07-08T22:40:15Z","abstract_excerpt":"We present SOLO, a single transformer for Scalable visiOn-Language mOdeling. Current large vision-language models (LVLMs) such as LLaVA mostly employ heterogeneous architectures that connect pre-trained visual encoders with large language models (LLMs) to facilitate visual recognition and complex reasoning. Although achieving remarkable performance with relatively lightweight training, we identify four primary scalability limitations: (1) The visual capacity is constrained by pre-trained visual encoders, which are typically an order of magnitude smaller than LLMs. (2) The heterogeneous archite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06438","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/2407.06438/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":"2407.06438","created_at":"2026-07-05T09:49:07.574840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06438v3","created_at":"2026-07-05T09:49:07.574840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06438","created_at":"2026-07-05T09:49:07.574840+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ2HYQJJJTSB","created_at":"2026-07-05T09:49:07.574840+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ2HYQJJJTSBIXGP","created_at":"2026-07-05T09:49:07.574840+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ2HYQJJ","created_at":"2026-07-05T09:49:07.574840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12566","citing_title":"Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW","json":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW.json","graph_json":"https://pith.science/api/pith-number/ZQ2HYQJJJTSBIXGPFTWINYARAW/graph.json","events_json":"https://pith.science/api/pith-number/ZQ2HYQJJJTSBIXGPFTWINYARAW/events.json","paper":"https://pith.science/paper/ZQ2HYQJJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW","download_json":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW.json","view_paper":"https://pith.science/paper/ZQ2HYQJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06438&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ2HYQJJJTSBIXGPFTWINYARAW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ2HYQJJJTSBIXGPFTWINYARAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ2HYQJJJTSBIXGPFTWINYARAW/action/replication_record"}},"created_at":"2026-07-05T09:49:07.574840+00:00","updated_at":"2026-07-05T09:49:07.574840+00:00"}