arXiv cs.CL
· Papers
Stuck on "A": Diagnosing and Repairing Interface Injury in Attention-to-KDA Linearization of a 0.6B Language Model
arXiv:2608.02689v1 Announce Type: new Abstract: We convert 21 of 28 full-attention layers of Qwen3-0.6B-Base into KDA (Kimi Delta Attention) linear-attention layers on a single consumer-grade GPU budget, and ask a simple question: what exactly does the conversion break? After surgery, hidden-state alignment and end-to-