Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression

ArXi:2604.21335v1 Announce Type: new Sub-token routing offers a finer control axis for transformer efficiency than the coarse units used in most prior work, such as tokens, pages, heads, or layers. In this paper, we study routing within a token representation itself in LoRA-adapted transformers. The motivation is that a relevant token need not be internally uniform: under a retention budget, preserved value groups are distributed unevenly both across tokens and within tokens, which suggests that KV compression need not be an all-or-nothing decision at token level.