Yongpan Liu

ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression

2020 · arXiv (Cornell University)

Despite the recent progress of network pruning, directly applying it to the Internet of Things (IoT) applications still faces two challenges, i.e. the distribution divergence between end and cloud data and the missing of data …

A 28nm 3.14 TFLOP/W BF16 LLM Fine-Tuning Processor with Asymmetric Quantization Computing for AI PC

2025

The powerful capabilities of large language models (LLMs) enable them to function as personal digital assistants. To ensure user privacy, personalized fine-tuning can be conducted locally on memoryconstrained AI PCs using Parameter-Efficient Fine-Tuning (PEFT) algorithms, …