{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YPQBJSQA67JHVUMXFL3LSRWBOF","short_pith_number":"pith:YPQBJSQA","schema_version":"1.0","canonical_sha256":"c3e014ca00f7d27ad1972af6b946c1714d7dd9974a8cd60660fe1b29cd2c8d0d","source":{"kind":"arxiv","id":"2402.01831","version":3},"attestation_state":"computed","paper":{"title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arushi Goel, Bryan Catanzaro, Rafael Valle, Rohan Badlani, Wei Ping, Zhifeng Kong","submitted_at":"2024-02-02T18:58:34Z","abstract_excerpt":"Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various"},"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":"2402.01831","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-02T18:58:34Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"ae0bca3d1e6be7edd8c725aacd75cd805b2eabe957b85be3b1258f248a12853d","abstract_canon_sha256":"4a8bbea98d244aaababc61b8668cc3138ef4aeada2c4dc8d985ac2eb89efe945"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:00.653230Z","signature_b64":"UE8dTL/H/CPTPh4V88EDe+xkzen8dWiJCz7PU3IWnUp/r6uIc4N3EX/yw/T6yXMieQigmOlk7yg/RA0RPkDZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e014ca00f7d27ad1972af6b946c1714d7dd9974a8cd60660fe1b29cd2c8d0d","last_reissued_at":"2026-07-05T08:24:00.652723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:00.652723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arushi Goel, Bryan Catanzaro, Rafael Valle, Rohan Badlani, Wei Ping, Zhifeng Kong","submitted_at":"2024-02-02T18:58:34Z","abstract_excerpt":"Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01831","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/2402.01831/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":"2402.01831","created_at":"2026-07-05T08:24:00.652781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01831v3","created_at":"2026-07-05T08:24:00.652781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01831","created_at":"2026-07-05T08:24:00.652781+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPQBJSQA67JH","created_at":"2026-07-05T08:24:00.652781+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPQBJSQA67JHVUMX","created_at":"2026-07-05T08:24:00.652781+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPQBJSQA","created_at":"2026-07-05T08:24:00.652781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11260","citing_title":"RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18273","citing_title":"Continuous Audio Thinking for Large Audio Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05121","citing_title":"Audio Interaction Model","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31338","citing_title":"Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28480","citing_title":"Audio-Mind: An Auditable Agentic Framework for Audio Understanding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2512.02231","citing_title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24401","citing_title":"All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2407.10759","citing_title":"Qwen2-Audio Technical Report","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13804","citing_title":"Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12527","citing_title":"Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13023","citing_title":"SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF","json":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF.json","graph_json":"https://pith.science/api/pith-number/YPQBJSQA67JHVUMXFL3LSRWBOF/graph.json","events_json":"https://pith.science/api/pith-number/YPQBJSQA67JHVUMXFL3LSRWBOF/events.json","paper":"https://pith.science/paper/YPQBJSQA"},"agent_actions":{"view_html":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF","download_json":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF.json","view_paper":"https://pith.science/paper/YPQBJSQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01831&json=true","fetch_graph":"https://pith.science/api/pith-number/YPQBJSQA67JHVUMXFL3LSRWBOF/graph.json","fetch_events":"https://pith.science/api/pith-number/YPQBJSQA67JHVUMXFL3LSRWBOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF/action/storage_attestation","attest_author":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF/action/author_attestation","sign_citation":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF/action/citation_signature","submit_replication":"https://pith.science/pith/YPQBJSQA67JHVUMXFL3LSRWBOF/action/replication_record"}},"created_at":"2026-07-05T08:24:00.652781+00:00","updated_at":"2026-07-05T08:24:00.652781+00:00"}