#the study

MoonshotAI (Kimi) proposed AttnRes to replace Transformer's residual connection with Attention, 1.25 times more computationally efficient.

AttnRes to replace Transformer's fixed residual combination with softmax attention in the depth direction. Demonstration with Kimi Linear 48B improved GPQA-Diamond +7.5pt and HumanEval +3.1pt. Training overhead was kept below 4% and inference below 2%.