Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
Ziyu Zhao, Tong Zhu, Zhi Zhang +6
Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scra…
cs.CL2025
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
Kairong Han, Wenshuo Zhao, Ziyu Zhao +3
Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for pre…