activity
20222026
most citedEmpathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection

3 citations · 4 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Shaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation

Yaoxiang Wang, Kai Zhang, Ruobing Xie +4

Fine-grained mixture-of-experts (MoE) models commonly increase expert count by narrowing each expert, treating expert shape as a by-product of routing granularity. LatentMoE moves…