ParaTTT parallelizes deep nonlinear test-time training memories
Two refinement steps at 4K context evaluate the inner-loop trajectory 32× faster than TTT-MLP at matched error.
Stories per day · 30 days
1 RSS
2 stories, newest first · one card per story
Stories tagged #recurrent-models
Learning Length-Extrapolatable Recurrent Models
Researchers propose Credit Stabilization through Time, a training method letting recurrent models extrapolate up to 128x their training length.