🧑🔬 Wenxiao Wang — papers of 2026 — 1 paper, the most cited first1 paper · all years of Wenxiao WangHeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM InferenceAnnual Meeting of the Association for Computational Linguistics (ACL)Zhiyuan Shi, Qibo Qiu, Xuefeng, et al.2026This page in Markdown → https://md.research.elamur.ai/free/en/authors/wenxiao-wang/year/2026/