I started working with Prof. Hongcheng Guo's lab at Fudan University this summer. We are happy to collaborate on multi-agent systems and have started several projects together.
About
About Me
I am a Ph.D. student at KAUST under the supervision of Prof. Panos Kalnis.
My research interests include machine learning systems, system acceleration, and distributed ML inference.
Updates
News
2026
2025
I successfully completed my internship. During the internship, I helped release the KunServe codebase as open source. I am grateful to the professors and fellow students I met for their guidance and support.
From May to late August 2025, I interned with the IPADS group at Shanghai Jiao Tong University under the supervision of Prof. Xingda Wei. My research focused on elastic LLM serving, specifically the KUNSERVE system.
Selected work
View all
Publications
EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision
arXiv preprint · 2026
Evolves multi-agent prompts and topology from recurring evidence-guided diagnoses, accepting revisions only after paired validation improves accuracy or cost.
Exploring a Layer-Wise Design Space for KV Cache Eviction
arXiv preprint · 2026
Explores layer-wise composition of existing KV-cache eviction methods, showing that heterogeneous routing and profile-guided placement improve long-context quality under matched cache budgets.
CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference
arXiv preprint · 2026
Combines context-aware hierarchical KV selection with coarse-grained system support to retain quality while accelerating long-context decoding.