20 citations · 20 across the 3 of their papers we have counts for
5 papers
CacheSmith: Accurate RAG Serving under Latency SLOs with Adaptive KV Reuse
Xinyue Ma, Damin Lee, Aashaka Shah +1
This paper presents CacheSmith, a KV cache reuse system for RAG prefill that maximizes quality-gated SLO attainment. While context caching lowers prefill latency by reusing precomp…
DIALER: A Case for Improving Rare-Class Accuracy in Retraining-Free Edge Video Analytics
Dongyoon Ryu, Sungho Jeon, Xinyue Ma +4
Edge video analytics with lightweight models is prone to accuracy degradation due to persistent distributional shifts in live video streams. While continuous learning (CL) addresse…
OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration
Xinyue Ma, Heelim Hong, Taegeon Um +4
Serving long-context LLMs is challenging because request lengths and batch composition vary during token generation, causing the memory footprint to fluctuate significantly at runt…
REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
Sungho Jeon, Xinyue Ma, Kwang In Kim +1
Recent rehearsal-free continual learning (CL) methods guided by prompts achieve strong performance on vision tasks with non-stationary data but remain resource-intensive, hindering…
Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
Xinyue Ma, Suyeon Jeong, Minjia Zhang +3
Continual learning (CL) trains NN models incrementally from a continuous stream of tasks. To remember previously learned knowledge, prior studies store old samples over a memory hi…