Yuan Meng

5

Papers

54

Total Citations

Papers (5)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

ACL: Activating Capability of Linear Attention for Image Restoration

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration

Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning