Tra-MoE: learning trajectory prediction model from multiple domains for adaptive policy conditioningApr 20, 2025·Jiange Yang,Haoyi Zhu,Yating Wang,Gangshan Wu,Tong HeLimin Wang· 0 min read Cite URLTypeConference paperPublicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern RecognitionLast updated on Apr 20, 2025AuthorsLimin WangNanjing University← Taste more, taste better: diverse data and strong model boost semi-supervised crowd counting Apr 20, 2025Uniap: unifying inter-and intra-layer automatic parallelism by mixed integer quadratic programming Apr 20, 2025 →
