2 citations · 2 across the 2 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Accelerating Dense LLMs via L0-regularized Mixture-of-Experts
Zhenyu Zhang, Jiudong Yang, Zhaowen Tao +1
Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeable performance degradation, w…
cs.LG2026
POSPAN: Position-Constrained Span Masking for Language Model Pre-training
Zhenyu Zhang, Lei Shen, Yuming Zhao +2
Span-level masked language modeling (MLM) has shown to be advantageous to pre-trained language models over the original single-token MLM, as entities/phrases and their dependencies…