Recently updated channels

Pick one to see only that channelBrowse all channels →
AI Engineeryesterday硅谷101yesterdayPragerU2 days agoY Combinator2 days agoSemiAnalysis3 days agoGOTO Conferences3 days agoLatent Space4 days agoDwarkesh Patel4 days agoAdrian Twarog5 days agoHow I AI5 days ago

Results

2 articles
Sort
TopicVoice AILength15–30 min
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
17:21EN
Lex FridmanPodcast · 2 speakersHow Alexa Learned to Hear From Across the Room: Rohit Prasad on Far-Field Speech and IntentGuest Rohit Prasad · Host Lex FridmanAlexa's head scientist recalls the early days of the Echo, when far-field speech recognition seemed unsolvable and there were no customers to collect data from.Multimodal & mediaVoice AIProduct engineering+2