註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Azalia Mirhoseini
@Azaliamirh
Founder @RicursiveAI, Asst. Prof. of CS at Stanford. Prev: DeepMind, Anthropic, Brain. Co-Creator of MoEs, AlphaChip, Test Time Scaling.
加入 May 2013
626 正在關注    20.3K 粉絲
Thank you @VentureBeat for covering our work on Decentralized Language Models (DeLM)! DeLM makes agentic tasks like coding and multi-doc Q&A more accurate and significantly cheaper, e.g. a ~10% jump on SWE-bench Verified with Gemini-3 Flash at less than half the cost. @Mao_Yuzhen
顯示更多
A new Stanford framework called a decentralized language model, or DeLM, is built on the premise that #AI# agents can coordinate directly, without routing every update through a central controller. #ArtificialIntelligence# #GenerativeAI#
顯示更多
0
4
103
13
轉發到社區