{"paper":{"title":"Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Mourachko, Artyom Kozhevnikov, Belen Alastruey, Christophe Ropers, David Dale, Guillem Ram\\'irez, Holger Schwenk, Ioannis Tsiamas, Jaehyeong Jo, Kevin Heffernan, Loic Barrault, Marta R. Costa-Jussa, Omnilingual SONAR Team: Jo\\~ao Maria Janeiro, Paul-Ambroise Duquenne, Pere-Llu\\'is Huguet Cabot, Vivek Iyer, Xiang \"Tony\" Cao, Yen Meng, Yu-An Chung","submitted_at":"2026-03-17T14:47:35Z","abstract_excerpt":"Cross-lingual sentence encoders typically cover only a few hundred languages and often trade downstream quality for stronger alignment, limiting their adoption. We introduce OmniSONAR, a new family of omnilingual, cross-lingual and cross-modal sentence embedding models that natively embed text, speech, code, and mathematical expressions in a single semantic space, while delivering state-of-the-art downstream performance at the scale of thousands of languages, from high-resource to extremely low-resource varieties. To reach this scale without representation collapse, we use progressive training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16606","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/2603.16606/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"}