The Gating Mechanism of KV Cache Evictionwith Hao Gu, Xintong Yang, Zhiwei Li, Lei Zhu +81 versionW_emm2b9uvv1 · current
Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient ReasoningQiyuan Zhu, Dezhi Li, Pengyu Cheng et al.0 citations2608.04771v12026arXiv
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM InferenceXintong Yang, Hao Gu, Binxing Xu et al.0 citations2605.25475v22026arXiv
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research AutomationJinhang Xu, Qiyuan Zhu, Yujun Wu et al.0 citations2605.10813v22026arXiv
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert MergingLujun Li, Zhu Qiyuan, Jiacheng Wang et al.3 citations2506.23266v12025arXiv
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary CodebookHao Gu, Lujun Li, Hao Wang et al.0 citations2506.12040v22025arXiv