Meta FAIR releases e-means, claiming 10x fewer epochs than k-means
The captured page is only a cookie notice, so datasets, code, and benchmark numbers are not available.
1
2 stories, newest first · one card per story
The captured page is only a cookie notice, so datasets, code, and benchmark numbers are not available.

Meta FAIR, Oxford and UCL introduce Research Preference Models that rank unexecuted ML experiments, lifting AIRS-Bench scores from 0.684 to 0.729 and cutting compute ~1.6×.
Today 1.6K readers · 2.4K views · 776 reads · all time 189K views