Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
InfiLoop adds loop-native residuals so looped Transformers keep improving past 20,000 test-time steps.
1 stories, newest first · one card per story
InfiLoop adds loop-native residuals so looped Transformers keep improving past 20,000 test-time steps.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views