Xinhang Chen — accepted AI-conference papers

2026

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs

Yanlin Qi, Xinhang Chen, Huiqiang Jiang, Qitong Wang, Botao Peng, Themis Palpanas

ICML 2026poster

KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce **ParisKV**, a drift-robust, GPU-native KV-cache retrieval framework based on collision-based candidate selection, followed by a quantized inn…

Cited by 0 Source ↗Scholar ↗

2026

Predicting Future KV Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction

Ziyao Tang, Pengkun Jiao, Xinhang Chen, LiuWei Liu, Shiyong Li, Jingjing Chen

ICML 2026poster

Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are consistent proxies for importance across all heads. However, this …

Cited by 0 Source ↗Scholar ↗