{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NNHAX3QVBWEST5EJVOP2CPUVCR","short_pith_number":"pith:NNHAX3QV","schema_version":"1.0","canonical_sha256":"6b4e0bee150d8929f489ab9fa13e95147dd1db8141148a6bf2382e0aaeac7897","source":{"kind":"arxiv","id":"2406.10056","version":1},"attestation_state":"computed","paper":{"title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dongchao Yang, Haohan Guo, Helen Meng, Rongjie Huang, Xiang Li, Xixin Wu, Xu Tan, Yuanyuan Wang","submitted_at":"2024-06-14T14:13:18Z","abstract_excerpt":"The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning approach, empowering the frozen LLMs to achieve multiple audio tasks in a few-shot style without any parameter update. Specifically, we propose a novel and LLMs-driven audio codec model, LLM-Codec, to transfer the audio modality into the textual space, \\textit{i.e.} representing audio tokens with words or sub-words in the vocabulary of LLMs, while keeping high "},"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":"2406.10056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:13:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ee7bd0ec8009d1ed5ed728c3200620fc8a83f118c4ba2ea04e6bb9306b731ee1","abstract_canon_sha256":"6943b16faa0983890dd732f04a61fa7a5ec1a3333f59f1ee3c978eac3ed8e411"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:03.918567Z","signature_b64":"mRxDlpCrxz6LlWMpval7JxNjr14NVnU4i+VhO7T3Qmua07wozZ/Ti3mBs1Fq70LS7+Tt/jmaKKFLyl0g2hiKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b4e0bee150d8929f489ab9fa13e95147dd1db8141148a6bf2382e0aaeac7897","last_reissued_at":"2026-07-05T08:32:03.918092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:03.918092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dongchao Yang, Haohan Guo, Helen Meng, Rongjie Huang, Xiang Li, Xixin Wu, Xu Tan, Yuanyuan Wang","submitted_at":"2024-06-14T14:13:18Z","abstract_excerpt":"The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning approach, empowering the frozen LLMs to achieve multiple audio tasks in a few-shot style without any parameter update. Specifically, we propose a novel and LLMs-driven audio codec model, LLM-Codec, to transfer the audio modality into the textual space, \\textit{i.e.} representing audio tokens with words or sub-words in the vocabulary of LLMs, while keeping high "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10056","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/2406.10056/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":"2406.10056","created_at":"2026-07-05T08:32:03.918150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10056v1","created_at":"2026-07-05T08:32:03.918150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10056","created_at":"2026-07-05T08:32:03.918150+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNHAX3QVBWES","created_at":"2026-07-05T08:32:03.918150+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNHAX3QVBWEST5EJ","created_at":"2026-07-05T08:32:03.918150+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNHAX3QV","created_at":"2026-07-05T08:32:03.918150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02443","citing_title":"Breaking the Barriers of Text-Hungry and Audio-Deficient AI","ref_index":150,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR","json":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR.json","graph_json":"https://pith.science/api/pith-number/NNHAX3QVBWEST5EJVOP2CPUVCR/graph.json","events_json":"https://pith.science/api/pith-number/NNHAX3QVBWEST5EJVOP2CPUVCR/events.json","paper":"https://pith.science/paper/NNHAX3QV"},"agent_actions":{"view_html":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR","download_json":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR.json","view_paper":"https://pith.science/paper/NNHAX3QV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10056&json=true","fetch_graph":"https://pith.science/api/pith-number/NNHAX3QVBWEST5EJVOP2CPUVCR/graph.json","fetch_events":"https://pith.science/api/pith-number/NNHAX3QVBWEST5EJVOP2CPUVCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/action/storage_attestation","attest_author":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/action/author_attestation","sign_citation":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/action/citation_signature","submit_replication":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/action/replication_record"}},"created_at":"2026-07-05T08:32:03.918150+00:00","updated_at":"2026-07-05T08:32:03.918150+00:00"}