most citedOmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization

2 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

SPRI: SVD-Partitioned Residual Initialization for Data-Constrained MoE Upcycling

Weiqiao Shan, Ruixiang Mao, Yuang Li +10

Mixture-of-Experts (MoE) models enable efficient scaling, but training them from scratch remains prohibitively expensive. MoE upcycling mitigates this cost by converting pretrained…