List your company

Sequence Copying on Toy Vocabulary 1K sequences (held-out)

100AccuracyBaseline
9597.5100102.5Apr 18, 2026

Evaluation results

MethodLinks
BaselineModel Dimension (d)=128, Number of Layers (L)=62026.041001.012100—
TSAModel Dimension (d)=128, Number of Layers (L)=62026.041001.01234.154.9