{"paper":{"title":"MinMo: A Multimodal Large Language Model for Seamless Voice Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Bin Ma, Changfeng Gao, Chong Deng, Chongjia Ni, Chong Zhang, Fan Yu, Guanrou Yang, Haoneng Luo, Hao Wang, Hui Wang, Jialong Tang, Jiaqing Liu, Jinren Zhou, Mengzhe Chen, Nan Zhao, Pei Zhang, Qian Chen, Qinglin Zhang, Ruize Gao, Shiliang Zhang, Tianyu Zhao, Wen Wang, Xiang Lv, Xian Shi, Xian Yang, Yabin Li, Yafeng Chen, Yanni Chen, Yexin Yang, Yingda Chen, Yunlan Xu, Yuxuan Wang, Zhifu Gao, Zhihao Du, Zhijie Yan","submitted_at":"2025-01-10T15:55:27Z","abstract_excerpt":"Recent advancements in large language models (LLMs) and multimodal speech-text models have laid the groundwork for seamless voice interactions, enabling real-time, natural, and human-like conversations. Previous models for voice interactions are categorized as native and aligned. Native models integrate speech and text processing in one framework but struggle with issues like differing sequence lengths and insufficient pre-training. Aligned models maintain text LLM capabilities but are often limited by small datasets and a narrow focus on speech tasks. In this work, we introduce MinMo, a Multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06282","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/2501.06282/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"}