Guangxuan Xiao

AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration

Ji Lin, Jiaming Tang, Haotian Tang et al. · GetMobile Mobile Computing and Communications · 2025 · 132 citations

Engineering, Advanced Computing, Computer Architecture +19

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Guangxuan Xiao, Ji Lin, Mickaël Seznec · arXiv (Cornell University) · 2022 · 96 citations · Full text

Efficient Post-training Quantization, Structured Prediction, Llm Fine-tuning +20

FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention

Guangxuan Xiao, Tianwei Yin, William T. Freeman et al. · International Journal of Computer Vision · 2024 · 91 citations · Full text

Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor Attacks

Zhengyan Zhang, Guangxuan Xiao, Yongwei Li et al. · Machine Intelligence Research · 2023 · 36 citations · Full text

Llm Fine-tuning, Engineering, Machine Learning +18

Offsite-Tuning: Transfer Learning without Full Model

Guangxuan Xiao, Ji Lin, Song Han · arXiv (Cornell University) · 2023 · 21 citations · Full text

Privacy Protection, Engineering, Machine Learning +21