Author

Zhi-Yu Wang

h-index 5 View on Semantic Scholar

We have 3 of 20 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#edge computing Review Open access Aug 2026

Artificial intelligence-driven resource management in edge-cloud computing continuum for internet of things applications: new trends and future directions

This review examines emerging trends in Artificial Intelligence (AI)-driven resource management within this continuum, with a focus on three directions: the transition from centralized to distributed and collaborative intelligence, cross-domain adaptation and knowledge transfer for heterogeneous IoT applications, and the nascent integration of foundation models into edge environments.

Zhi-Yu Wang, Nilotpal Kapri, L. Bittencourt et al. · Frontiers in The Internet of... · 0 citations

Preprint Aug 2026

PrefixPlace: Provable Prefix Key-Value Placement for Large Language Model Serving under Heterogeneous Compute and Transfer Costs

An epoch-level planner, PrefixPlace, which assigns prefix-complete targets under memory budgets and profiled demand, compute, and transfer costs, and solves a 50,000-node, 16-worker placement in 12.3 s on one processor, enabling timely replanning.

Zhiyu Wang, Rajkummar Buyya · 0 citations

Preprint Aug 2026

Preserving Admission Responsibility in Multi-Tenant Large Language Model Prefix Caches

Results show that object-value signals rank what to retain, while persistent responsibility determines which group bears reclamation pressure, which shows that object-value signals rank what to retain, while persistent responsibility determines which group bears reclamation pressure.

Zhiyu Wang, Rajkummar Buyya · 0 citations