activity
20222026
most citedPIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions

5 citations · 16 across the 38 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…