🌕 Gate Square · Mid-Autumn Creator Incentive Program is Live!
Share trending topic posts, and split $5,000 in prizes! 🎁
👉 Check details & join: https://www.gate.com/campaigns/1953
💝 New users: Post for the first time and complete the interaction tasks to share $600 newcomer pool!
🔥 Today's Hot Topic: #MyTopAICoin#
Altcoins are heating up, AI tokens rising! #WLD# and #KAITO# lead the surge, with WLD up nearly 48% in a single day. AI, IO, VIRTUAL follow suit. Which potential AI coins are you eyeing? Share your investment insights!
💡 Post Ideas:
1️⃣ How do you see AI tokens evolving?
2️⃣ Wh
Alitongyi Open Source audio language model Qwen2-Audio, related paper selected for top conference ACL 2024
Jinshi data, August 13 news, Ali Tongyi's large model continues to be Open Source, and the Qwen2 series Open Source family has added the audio language model Qwen2-Audio. Qwen2-Audio can directly perform voice Q&A without the need for text input, understand and analyze the audio signals input by users, including human voice, natural sound, music, etc. The model has significantly surpassed the previous best models in multiple authoritative evaluations. Tongyi team also simultaneously released a new trap audio understanding model evaluation Benchmark, and the related paper has been selected for the international top conference ACL2024 being held this week.