2 papers
cs.LG2026
HiER-BLS: A Hierarchy-Guided and Error-Correcting Robust Incremental Broad Learning System
Gongli Zhang, C. L. Philip Chen, Zhulin Liu
Broad Learning System (BLS) supports analytical training and incremental expansion, but its growth needs guidance on which inputs new blocks should learn from. Weight errors pose a…
cs.LG2026
Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation
Gongli Zhang, Zhulin Liu, C. L. Philip Chen
Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts. Shared-expert designs preserve reusable knowledge, fine-grained methods vary…