Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermantoday +1Theo - t3․ggyesterday +74AI Engineeryesterday +2a16z2 days ago +1The Builders2 days ago +1硅谷1012 days ago +1SemiAnalysis2 days ago +1Chris Williamson2 days agoCheeky Pint2 days agoInvest Like The Best2 days ago

Results

1 articles
Sort
TopicVoice AILanguageSimplified Chinese
16 slides23:39ZH → English
跟李沐学AI· Jul 23, 2025Li Mu: Adding Ten Million Hours of Speech to a Text LLM, Open-Sourcing Higgs Audio李沐 · Boson AILi Mu explains how the team added a huge amount of speech data to text LLM training, built an AudioLLM that can listen and speak, and open-sourced Higgs Audio. He covers architecture trade-offs, token compression, where the data came from, and how to run it on a 3090.Voice AIMultimodal AIModels & training+2