3 papers
cs.LG2026
DBES: A Systematic Benchmark and Metric Suite for Evaluating Expert Specialization in Large-Scale MoEs
Jing Wang, Hongxuan Lu, Jazze Young +2
Expert specialization in Mixture-of-Experts (MoE) models remains poorly understood, with traditional evaluations conflating architectural load-balancing with functional specializat…
cs.SD2024
Complexity boosted adaptive training for better low resource ASR performance
Hongxuan Lu, Shenjian Wang, Biao Li
During the entire training process of the ASR model, the intensity of data augmentation and the approach of calculating training loss are applied in a regulated manner based on pre…
cs.SD2024
Sample adaptive data augmentation with progressive scheduling
Hongxuan Lu, Biao Li
Data augmentation is a widely adopted technique utilized to improve the robustness of automatic speech recognition (ASR). Employing a fixed data augmentation strategy for all train…