arXiv:2606. 01563v1 Announce Type: new Abstract: Autoregressive decoding in Transformer-based language models relies on the KV cache, whose memory footprint grows linearly with sequence length and becomes the primary bottleneck for long-context inference.
By Yu Li, Binxu Li, Tian Lan
arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.
By Vishwajith Ramesh
ValueDiff introduces a value‑geometric KV cache eviction strategy for large language models that suppress attention sinks. It ranks tokens by the L2 deviation of their value vectors from the cache mean, a score that aligns with minimal‑disturbance eviction under a max‑entropy assumption. Across several benchmarks—RULER, LongBench, and MATH‑500—ValueDiff consistently retains a higher proportion of useful tokens than prior methods, especially under tight cache budgets.
By Junyoung Park, Jungwook Choi, Mingu Lee
arXiv:2607. 07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantization, eviction, or offloading.
By Vladimir Gusev
arXiv:2608. 26515v1 Announce Type: cross Abstract: We study online prediction for a specific finite-alphabet, exogenously driven source with infinite input memory.
By Vaneet Aggarwal
The paper introduces Window-Diffusion, a method that accelerates diffusion language model inference by pruning and caching tokens within a sliding window. It categorizes undecoded tokens into active, buffer, and far-field groups, computing only the first two while discarding the rest. Experiments on LLaDA and Dream demonstrate up to 99× speedup with minimal loss in generation quality.
By Fengrui Zuo, Zhiwei Ke, Yiming Liu, Wenqi Lou, Chao Wang, Xuehai Zhou