1
Linearizing Vision Transformer with Test-Time Training
提出测试时训练新范式，将Vision Transformer复杂度从二次降至线性，推理时仅需少量计算即可大幅提升准确率和鲁棒性。
arXiv:2605.02772v2 Announce Type: replace Abstract: While linear-complexity attention mechanisms offer a promising alternative to Softmax attention fo…