4 papers
Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models
Shijin Gong, Baihua He, Xinyu Zhang
Conditional generative models have emerged as powerful tools for sampling from target conditional distributions, driving substantial advances across a wide range of scientific and…
Combining pre-trained models via localized model averaging
Ziwen Gao, Baihua He, Yuhong Yang
Many pre-trained models (PTMs) are available in modern applications. Because different PTMs are often trained on different datasets, their performances can vary substantially for d…
Saliency-Aware Regularized Quantization Calibration for Large Language Models
Yanlong Zhao, Xiaoyuan Cheng, Huihang Liu +6
Post-training quantization (PTQ) is an effective approach for deploying large language models (LLMs) under memory and latency constraints. Most existing PTQ methods determine quant…
Representation Transfer Learning for Semiparametric Regression
Baihua He, Huihang Liu, Xinyu Zhang +1
We propose a transfer learning method that utilizes data representations in a semiparametric regression model. Our aim is to perform statistical inference on the parameter of prima…