2 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.CV2026
Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs
Pengcheng Wang, Zhiquan Wang, Jayoung Lee +5
Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost, arising from both the large…