2 papers
cs.LG2026
IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference
Wanli Zhong, Haibo Feng, Zirui Zhou +2
Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multiplications, it expose…
cs.CV2025
Pose as Clinical Prior: Learning Dual Representations for Scoliosis Screening
Zirui Zhou, Zizhao Peng, Dongyang Jin +3
Recent AI-based scoliosis screening methods primarily rely on large-scale silhouette datasets, often neglecting clinically relevant postural asymmetries-key indicators in tradition…