arXiv:2610.18654v1 Announce Type: cross
Abstract: Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants...
By OneRec Team, Chenglong Chu, Guohong Mu, Guowang Zhang, Hao Peng, Hui Wang, Jian Liang, Jiangxia Cao, Jiao Ou, Jiaxin Deng, Lu Ren, Muhao Wei, Ruiming Tang, Tianle Xu, Wenwu Ou, Xingmei Wang, Zhixin Ling, Zhiyuan Liang, Ziqi Wang, Chaoyi Ma, Haixiao Gao, Kuo Cai, Renpu Liu, Ruochen Yang, Wenlong Xu, Xinqi Jin, Yan Sun, Yifan Wang, Yingzhi He, Yiyu Wang, Yusen Huo, Zhaojie Liu, Zihan Zhou
SGD-KV is a head‑aware framework for compressing key‑value caches in large language models. It uses a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation, allowing the KV cache budget to be allocated based on each head’s summarization score. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B show state‑of‑the‑art performance on up to 1M‑token contexts while cutting KV cache memory usage by up to 75%.
By Zeyu Liu, Woomin Song, Xuandi Fu, Sai Muralidhar Jayanthi, Vivek Govindan, Aram Galstyan, Sravan Babu Bodapati, Srikanth Ronanki
SGD-KV is a head‑aware framework that compresses key‑value caches in large language models by using a chunk‑summarization diagnostic task to identify attention heads that specialize in hierarchical information aggregation. It prioritizes these heads during compression, achieving state‑of‑the‑art performance on long‑context benchmarks with up to 1M tokens while cutting KV cache memory usage by as much as 75%. Experiments on Qwen2.5‑7B‑1M and Qwen3‑32B confirm that allocating cache budget based on summarization scores yields a superior efficiency‑accuracy trade‑off for long‑context inference.
arXiv:2604. 24432v2 Announce Type: replace-cross Abstract: Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system.
By Chenglong Chu, Guorui Zhou, Guowang Zhang, Han Li, Hao Peng, Hongtao Cheng, Hui Wang, Jian Liang, Jiangxia Cao, Kun Gai, Lingzhi Zhou, Lu Ren, Qi Zhang, Ruiming Tang, Ruitao Wang, Xinchen Luo, Yi Su, Zhiyuan Liang, Ziqi Wang, Boyang Ding, Chengru Song, Dunju Zang, Jiao Ou, Jiaxin Deng, Jijun Shi, Jinghao Zhang, Junmin Chen, Lejian Ren, Minxuan Lv, Qianqian Wang, Qigen Hu, Shiyao Wang, Siyang Mao, Tao Wang, Xingmei Wang, Zhixin Ling, Ziming Li, Zixing Zhang
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
By Soumia Bouyahiaoui, Manel Kara laouar, Aicha Boutorh, Mohamed Hadj Ameur
The paper introduces GRKV, a training‑free method for compressing the key‑value cache in long‑context large language models. GRKV uses ridge‑regression to redistribute information from evicted tokens to retained ones, aiming to minimize the difference between compressed‑cache and full‑cache attention outputs. Experiments on LongBench and RULER show that GRKV improves overall performance with minimal overhead compared to other merging methods.
By Junjie Peng, You Wu, Haoyi Wu, Jialong Han, Xiaohua Xie, Kewei Tu, Jianhuang Lai