long-context memory 1model efficiency 1retrieval-augmented generation 1self-distillation 1transformer depth division 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory
Hanzuo Liu, Xuan Qi, Chunyu Liu +6
The paper proposes CoMem, a method that stores intermediate transformer layer states as memory to enable efficient long‑context retrieval, showing that using lower‑mid layers for c…
cs.LG2026
SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask
Liu Hanzuo, Chaofan Lin, Weixuan Sun +4
Semi-structured sparsity provides a practical path to accelerate large language models (LLMs) with native hardware support, but post-training semi-structured pruning often suffers…