Zach Xu — accepted AI-conference papers

2026

Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving

Zongze Li, Jingyu Liu, Zach Xu, Yineng Zhang, Tahseen Rabbani, Ce Zhang

ICML 2026poster

Prefill-Decode (PD) disaggregation has become the standard architecture for modern LLM inference engines, which alleviates the interference of two distinctive workloads. With the growing demand for multi-turn interactions in chatbots and agentic systems, we re-examined PD in this case and found two …

Cited by 0 Source ↗Scholar ↗

2026

When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework

Zach Xu, Shang Zhu, Jue WANG, Junlin Wang, Ben Athiwaratkun, Chi Wang +2

ICLR 2026poster

We investigate the challenge of applying Large Language Models (LLMs) to long texts. We propose a theoretical framework that distinguishes the failure modes of long context tasks into three categories: cross-chunk dependence (task noise), confusion that grows with context size (model noise), and the…

Cited by 0 Source ↗code ↗Scholar ↗