{"work":{"id":"14b6b6ca-3c9e-434a-8eb7-ebdcbf08efc6","openalex_id":null,"doi":null,"arxiv_id":"2406.15704","raw_key":null,"title":"video-salmonn: Speech-enhanced audio-visual large language models.arXiv preprint arXiv:2406.15704,","authors":null,"authors_text":"Guangzhi Sun, Wenyi Yu, Changli Tang, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, Yuxuan Wang, and Chao Zhang","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2406.15704","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-18T05:45:56.080619+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T17:54:03.426620+00:00","updated_at":"2026-05-18T05:45:56.080619+00:00","title_quality_ok":true,"display_title":"video-salmonn: Speech-enhanced audio-visual large language models","render_title":"video-salmonn: Speech-enhanced audio-visual large language models"},"hub":{"state":{"work_id":"14b6b6ca-3c9e-434a-8eb7-ebdcbf08efc6","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":12,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2025-01-03T18:59:52+00:00","last_pith_cited_at":"2026-05-12T12:42:44+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-01T20:13:47.879246+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}