Xinyue Ma
I build efficient systems for large language models — long-context serving, KV cache reconfiguration, and continual learning on the edge. Advised by Professor Myeongjae Jeon, Graduate School of Artificial Intelligence, OMNIA at POSTECH.
Research Interests
Efficient Systems for LLMs
Continual Learning
Publications
ShoreKeeper: Accelerating Iterative Data Analytics in the Cloud via Distributed Recovery-Cost-Aware Caching
DIALER: A Case for Improving Rare-Class Accuracy in Retraining-Free Edge Video Analytics
ORBITFLOW: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration
REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Experience
2026.9 – 2026.12
2025.10.12 – 2024.10.13
Web Chair
2024.9 – 2024.12
Research Intern
Microsoft Research, Redmond — RiSE Group
Effective KV cache reuse for retrieval-augmented generation
2023.11 – 2024.2
Research Intern
Microsoft Research Asia — Intelligent Cloud & Edge Group
2024 – Present
Teaching Assistant
POSTECH
AI Systems (2025 Fall)
2022 – 2024
Teaching Assistant
UNIST
Computer Architecture (2023 Fall)
Parallel Computing (2022 Fall)
Advanced Programming (2022 Spring)