20 citations · 50 across the 29 of their papers we have counts for
7 papers · 1 filter
Prompt Diffusion Robustifies Any-Modality Prompt Learning
Yingjun Du, Gaowen Liu, Yuzhang Shang +3
Foundation models enable prompt-based classifiers for zero-shot and few-shot learning. Nonetheless, the conventional method of employing fixed prompts suffers from distributional s…
Distilling Long-tailed Datasets
Zhenghao Zhao, Haoxuan Wang, Yuzhang Shang +2
Dataset distillation aims to synthesize a small, information-rich dataset from a large one for efficient model training. However, existing dataset distillation methods struggle wit…
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
Kai Wang, Mingjia Shi, Yukun Zhou +6
Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a clos…
MIM4DD: Mutual Information Maximization for Dataset Distillation
Yuzhang Shang, Zhihang Yuan, Yan Yan
Dataset distillation (DD) aims to synthesize a small dataset whose test performance is comparable to a full dataset using the same model. State-of-the-art (SoTA) methods optimize s…
PB-LLM: Partially Binarized Large Language Models
Yuzhang Shang, Zhihang Yuan, Qiang Wu +1
This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due…
Lipschitz Continuity Retained Binary Neural Network
Yuzhang Shang, Dan Xu, Bin Duan +3
Relying on the premise that the performance of a binary neural network can be largely restored with eliminated quantization error between full-precision weight vectors and their co…
Lipschitz Continuity Guided Knowledge Distillation
Yuzhang Shang, Bin Duan, Ziliang Zong +2
Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although grea…