6 citations · 9 across the 23 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation
Yilong Chen, Naibin Gu, Junyuan Shang +8
Mixture-of-Experts (MoE) decouples model capacity from per-token computation, yet their scalability remains limited by the physical dimensions of depth and width. To overcome this,…
cs.LG2024
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
Yilong Chen, Linhao Zhang, Junyuan Shang +4
Large language models (LLMs) with billions of parameters demonstrate impressive performance. However, the widely used Multi-Head Attention (MHA) in LLMs incurs substantial computat…