2 papers
cs.AR2026
SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving
Hongyuan Liu, Yawei Li, Zhiqiang Que +3
Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost, yet even state-of-the-art 4-…
cs.CV2026
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
Hongyuan Liu, Qinli Yang, Wen Li +6
Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the m…