Researchers train AI model that hits near-full performance with just 12.5 percent of its experts
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.2 Articles
2 Articles
Researchers train AI model that hits near-full performance with just 12.5 percent of its experts
Researchers at the Allen Institute for AI and UC Berkeley have built EMO, a mixture-of-experts model whose experts specialize in content domains instead of word types. That lets you strip out three-quarters of the experts while losing only about one percentage point of performance, a step that could make MoE models practical for memory-constrained settings for the first time. The article Researchers train AI model that hits near-full performance…
Researchers at the Allen Institute for AI and UC Berkeley have developed a Mixture-of-Experts model with EMO, whose experts specialize in content domains rather than word types. This allows three quarters of experts to be removed, with only about one percentage point of power loss. This could make MoE models practical for the first time for storage-restricted environments. The article Researchers Train AI Model, which brings almost full performa…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
