2 papers
cs.LG2025
Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts
Fangshuo Liao, Anastasios Kyrillidis
Mixture-of-Experts (MoE) architectures have emerged as a cornerstone of modern AI systems. In particular, MoEs route inputs dynamically to specialized experts whose outputs are agg…
cs.LG2025
One Rank at a Time: Cascading Error Dynamics in Sequential Learning
Mahtab Alizadeh Vandchali, Fangshuo, Liao +1
Sequential learning -- where complex tasks are broken down into simpler, hierarchical components -- has emerged as a paradigm in AI. This paper views sequential learning through th…