3 papers
cs.LG2026
Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving
Xiang Li, Pengcheng Wang, Huazheng Wang +1
Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a critical system dilemma betwee…
cs.AI2025
Ascendra: Dynamic Request Prioritization for Efficient LLM Serving
Azam Ikram, Xiang Li, Sameh Elnikety +1
The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests th…
cs.CV2024
HopTrack: A Real-time Multi-Object Tracking System for Embedded Devices
Xiang Li, Cheng Chen, Yuan-yao Lou +3
Multi-Object Tracking (MOT) poses significant challenges in computer vision. Despite its wide application in robotics, autonomous driving, and smart manufacturing, there is limited…