{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FWGWN4M73HO27LS2COTOX3BUCZ","short_pith_number":"pith:FWGWN4M7","schema_version":"1.0","canonical_sha256":"2d8d66f19fd9ddafae5a13a6ebec34164399f5dea00cb1d96a87085e462f745f","source":{"kind":"arxiv","id":"2402.10896","version":2},"attestation_state":"computed","paper":{"title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Boyu Wang, Junfei Xiao, Shen Yan, Zheng Xu","submitted_at":"2024-02-16T18:54:47Z","abstract_excerpt":"This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have been extensively studied, the architecture and training strategy of vision-language adapters vary significantly across recent works. Our research undertakes a thorough exploration of the state-of-the-art perceiver resampler architecture and builds a strong baseline. However, we observe that the vision-language alignment with perceiver resampler exhibits slo"},"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":"2402.10896","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-16T18:54:47Z","cross_cats_sorted":[],"title_canon_sha256":"5415a4e495da78af6e8a9729c11f52f6962dec862b1e92f0aef21d250c8b0e94","abstract_canon_sha256":"ef843fc24fa570088030a9581680d8e5269829eb78af6d737fb49bc3a00a5dbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:52.596449Z","signature_b64":"qFaFslqhtOCx8LeMTYYNXmc2a2V+FzoXDhwSOxWgwRtK4lqkK6MW8FsJHnFL/8tmnOVe1+Pm+E0Eeo1JQsx7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d8d66f19fd9ddafae5a13a6ebec34164399f5dea00cb1d96a87085e462f745f","last_reissued_at":"2026-07-05T08:25:52.595906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:52.595906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Boyu Wang, Junfei Xiao, Shen Yan, Zheng Xu","submitted_at":"2024-02-16T18:54:47Z","abstract_excerpt":"This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have been extensively studied, the architecture and training strategy of vision-language adapters vary significantly across recent works. Our research undertakes a thorough exploration of the state-of-the-art perceiver resampler architecture and builds a strong baseline. However, we observe that the vision-language alignment with perceiver resampler exhibits slo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10896","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/2402.10896/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":"2402.10896","created_at":"2026-07-05T08:25:52.595966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10896v2","created_at":"2026-07-05T08:25:52.595966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10896","created_at":"2026-07-05T08:25:52.595966+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWGWN4M73HO2","created_at":"2026-07-05T08:25:52.595966+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWGWN4M73HO27LS2","created_at":"2026-07-05T08:25:52.595966+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWGWN4M7","created_at":"2026-07-05T08:25:52.595966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.01593","citing_title":"Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ","json":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ.json","graph_json":"https://pith.science/api/pith-number/FWGWN4M73HO27LS2COTOX3BUCZ/graph.json","events_json":"https://pith.science/api/pith-number/FWGWN4M73HO27LS2COTOX3BUCZ/events.json","paper":"https://pith.science/paper/FWGWN4M7"},"agent_actions":{"view_html":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ","download_json":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ.json","view_paper":"https://pith.science/paper/FWGWN4M7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10896&json=true","fetch_graph":"https://pith.science/api/pith-number/FWGWN4M73HO27LS2COTOX3BUCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FWGWN4M73HO27LS2COTOX3BUCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ/action/storage_attestation","attest_author":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ/action/author_attestation","sign_citation":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ/action/citation_signature","submit_replication":"https://pith.science/pith/FWGWN4M73HO27LS2COTOX3BUCZ/action/replication_record"}},"created_at":"2026-07-05T08:25:52.595966+00:00","updated_at":"2026-07-05T08:25:52.595966+00:00"}