Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction 文章

arXiv:2601.11667v2 Announce Type: replace-cross Abstract: Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or near-linear scaling yet often incur performance degradation. Hybrid models that integrate full and linear attention layers promise a balance between efficiency and expressiveness, but face two major challenges: training such hybrid models from scratch is computationally expensive, and manually designing the optimal placement of attention types is highly nontrivial. We propose DtR (Distill-then-Replace), which first transfers weights from the pretrained full-attention modules to its linear attention counterparts through blockwise local distillation, and then applies a greedy layer replacement strategy that iteratively substitutes full attention blocks with linear ones while monitoring…

摘要可能不完整，可查看原文