Zhi Zhang

ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns

PrunedLoRA: Robust Gradient-Based Structured Pruning for Low-rank Adaptation in Fine-tuning

Truncated Proximal Policy Optimization

DUO: No Compromise to Accuracy Degradation

Let the Code LLM Edit Itself When You Edit the Code

MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router