作者位次 #6/6CVPR 2026Poster· Computer Vision & Pattern Recognition
SegMo: Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient VLM Inference
Haojuan Li · Ruohan Tang · Dongzhou Cheng · Zongpu Zhang · Jian Li · Jiaqi Wang