{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FQ4WLK7P3WTSDZBOLGFVEUERHR","short_pith_number":"pith:FQ4WLK7P","schema_version":"1.0","canonical_sha256":"2c3965abefdda721e42e598b5250913c644f85b0a20e72febd300f737b2c973c","source":{"kind":"arxiv","id":"2412.16524","version":1},"attestation_state":"computed","paper":{"title":"LLaVA-SLT: Visual Language Tuning for Sign Language Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Tang, Chengyu Huang, Han Liang, Jingyi Yu, Juze Zhang, Lan Xu, Weicai Ye, Xin Chen, Yuecheng Xu","submitted_at":"2024-12-21T08:01:08Z","abstract_excerpt":"In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based approaches in terms of translation accuracy. To narrow this performance gap, we introduce LLaVA-SLT, a pioneering Large Multimodal Model (LMM) framework designed to leverage the power of Large Language Models (LLMs) through effectively learned visual language embeddings. Our model is trained through a trilogy. First, we propose linguistic continued pretraining"},"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":"2412.16524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T08:01:08Z","cross_cats_sorted":[],"title_canon_sha256":"a715041428bb0fa5dd1a57588f7da1d513c6fec3cccbb773649ce835546b013a","abstract_canon_sha256":"4cc2c3f80ba0c8f2d1a0fd141c78bd89ae13b1afc53403fd1d52350ef262c0b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:49.091266Z","signature_b64":"ZPCNSeQVWOAbOkQFmxt2z1Ux6og+JEHaWVGD2f3qnHh6agWuazXP/sQtpNvMqA+hJBNuh/plGXo/NU2AuPluCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c3965abefdda721e42e598b5250913c644f85b0a20e72febd300f737b2c973c","last_reissued_at":"2026-07-05T09:52:49.090826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:49.090826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaVA-SLT: Visual Language Tuning for Sign Language Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Tang, Chengyu Huang, Han Liang, Jingyi Yu, Juze Zhang, Lan Xu, Weicai Ye, Xin Chen, Yuecheng Xu","submitted_at":"2024-12-21T08:01:08Z","abstract_excerpt":"In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based approaches in terms of translation accuracy. To narrow this performance gap, we introduce LLaVA-SLT, a pioneering Large Multimodal Model (LMM) framework designed to leverage the power of Large Language Models (LLMs) through effectively learned visual language embeddings. Our model is trained through a trilogy. First, we propose linguistic continued pretraining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16524","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/2412.16524/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":"2412.16524","created_at":"2026-07-05T09:52:49.090886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16524v1","created_at":"2026-07-05T09:52:49.090886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16524","created_at":"2026-07-05T09:52:49.090886+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQ4WLK7P3WTS","created_at":"2026-07-05T09:52:49.090886+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQ4WLK7P3WTSDZBO","created_at":"2026-07-05T09:52:49.090886+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQ4WLK7P","created_at":"2026-07-05T09:52:49.090886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28626","citing_title":"SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22374","citing_title":"Selective Contrastive Learning For Gloss Free Sign Language Translation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11225","citing_title":"Sign Language Recognition in the Age of LLMs","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR","json":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR.json","graph_json":"https://pith.science/api/pith-number/FQ4WLK7P3WTSDZBOLGFVEUERHR/graph.json","events_json":"https://pith.science/api/pith-number/FQ4WLK7P3WTSDZBOLGFVEUERHR/events.json","paper":"https://pith.science/paper/FQ4WLK7P"},"agent_actions":{"view_html":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR","download_json":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR.json","view_paper":"https://pith.science/paper/FQ4WLK7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16524&json=true","fetch_graph":"https://pith.science/api/pith-number/FQ4WLK7P3WTSDZBOLGFVEUERHR/graph.json","fetch_events":"https://pith.science/api/pith-number/FQ4WLK7P3WTSDZBOLGFVEUERHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/action/storage_attestation","attest_author":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/action/author_attestation","sign_citation":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/action/citation_signature","submit_replication":"https://pith.science/pith/FQ4WLK7P3WTSDZBOLGFVEUERHR/action/replication_record"}},"created_at":"2026-07-05T09:52:49.090886+00:00","updated_at":"2026-07-05T09:52:49.090886+00:00"}