⚛️量子位•Stalecollected in 68m
Kaiming He's 105M LLM Skips GPT Autoregression
💡ResNet creator Kaiming He drops 105M non-autoregressive LLM paradigm shift
⚡ 30-Second TL;DR
What Changed
Kaiming He's first language model announced
Why It Matters
Innovative non-autoregressive approach may inspire efficient small LLMs. Could challenge dominant paradigms from top researcher.
What To Do Next
Follow Kaiming He's Twitter or arXiv for model paper and code.
Who should care:Researchers & Academics
Key Points
- •Kaiming He's first language model announced
- •105 million parameters scale
- •Non-autoregressive design unlike GPT
- •CV pioneer entering LLM field
📰
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: 量子位 ↗