Preprint
Jul 2026
Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory
These results show that long-context memory can be organized along the layer axis, not only the token axis, and expose both the benefits of bounded retrieval and its in-window compression tax.
Han-Lin Liu, Xuan Qi, Chunyu Liu et al.
· 0 citations