{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3W3UL66BMW3LIORLEB34GG5TBM","short_pith_number":"pith:3W3UL66B","schema_version":"1.0","canonical_sha256":"ddb745fbc165b6b43a2b2077c31bb30b038b85fc940b96217dc0356d6d09f2c7","source":{"kind":"arxiv","id":"2312.01564","version":1},"attestation_state":"computed","paper":{"title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dinesh Manocha, Sanjoy Chowdhury, Sayan Nag","submitted_at":"2023-12-04T01:42:09Z","abstract_excerpt":"The choice of input text prompt plays a critical role in the performance of Vision-Language Pretrained (VLP) models such as CLIP. We present APoLLo, a unified multi-modal approach that combines Adapter and Prompt learning for Vision-Language models. Our method is designed to substantially improve the generalization capabilities of VLP models when they are fine-tuned in a few-shot setting. We introduce trainable cross-attention-based adapter layers in conjunction with vision and language encoders to strengthen the alignment between the two modalities. We enforce consistency between the respecti"},"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":"2312.01564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-04T01:42:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"7e285d0b01f1f49f73d31e21259f1debd17a8caac414260361be818ff714e671","abstract_canon_sha256":"6e977b0adbc233658fe39d449cd8170b8d74530057fa11e61031f237998462a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:56.715335Z","signature_b64":"ef5XToETN5sFTcu7C/rRW3tm8MyJy40/AnyGrztwdinpy8FF7yw0NlsrrdvxijCuSLcK8vMqGWAdMn3w+sJDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddb745fbc165b6b43a2b2077c31bb30b038b85fc940b96217dc0356d6d09f2c7","last_reissued_at":"2026-07-05T07:19:56.714966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:56.714966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dinesh Manocha, Sanjoy Chowdhury, Sayan Nag","submitted_at":"2023-12-04T01:42:09Z","abstract_excerpt":"The choice of input text prompt plays a critical role in the performance of Vision-Language Pretrained (VLP) models such as CLIP. We present APoLLo, a unified multi-modal approach that combines Adapter and Prompt learning for Vision-Language models. Our method is designed to substantially improve the generalization capabilities of VLP models when they are fine-tuned in a few-shot setting. We introduce trainable cross-attention-based adapter layers in conjunction with vision and language encoders to strengthen the alignment between the two modalities. We enforce consistency between the respecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01564","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/2312.01564/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":"2312.01564","created_at":"2026-07-05T07:19:56.715026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01564v1","created_at":"2026-07-05T07:19:56.715026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01564","created_at":"2026-07-05T07:19:56.715026+00:00"},{"alias_kind":"pith_short_12","alias_value":"3W3UL66BMW3L","created_at":"2026-07-05T07:19:56.715026+00:00"},{"alias_kind":"pith_short_16","alias_value":"3W3UL66BMW3LIORL","created_at":"2026-07-05T07:19:56.715026+00:00"},{"alias_kind":"pith_short_8","alias_value":"3W3UL66B","created_at":"2026-07-05T07:19:56.715026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19128","citing_title":"One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM","json":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM.json","graph_json":"https://pith.science/api/pith-number/3W3UL66BMW3LIORLEB34GG5TBM/graph.json","events_json":"https://pith.science/api/pith-number/3W3UL66BMW3LIORLEB34GG5TBM/events.json","paper":"https://pith.science/paper/3W3UL66B"},"agent_actions":{"view_html":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM","download_json":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM.json","view_paper":"https://pith.science/paper/3W3UL66B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01564&json=true","fetch_graph":"https://pith.science/api/pith-number/3W3UL66BMW3LIORLEB34GG5TBM/graph.json","fetch_events":"https://pith.science/api/pith-number/3W3UL66BMW3LIORLEB34GG5TBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM/action/storage_attestation","attest_author":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM/action/author_attestation","sign_citation":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM/action/citation_signature","submit_replication":"https://pith.science/pith/3W3UL66BMW3LIORLEB34GG5TBM/action/replication_record"}},"created_at":"2026-07-05T07:19:56.715026+00:00","updated_at":"2026-07-05T07:19:56.715026+00:00"}