activity
20192023
most citedA Model Compression Method with Matrix Product Operators for Speech Enhancement

15 citations · 31 across the 8 of their papers we have counts for

collaborators

9 papers

cs.CV2023

A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation

Minghao Chen, Zepeng Gao, Shuai Zhao +4

Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. However, these methods necessitate a labeled target validation set…

cs.CL2023★ 1 cited

Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study

Peiyu Liu, Zikang Liu, Ze-Feng Gao +5

Despite the superior performance, Large Language Models~(LLMs) require significant computational resources for deployment and use. To overcome this issue, quantization methods have…

cs.CL2023

Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture

Peiyu Liu, Ze-Feng Gao, Yushuo Chen +2

In this paper, we propose a highly parameter-efficient approach to scaling pre-trained language models (PLMs) to a deeper model depth. Unlike prior work that shares all parameters…

cs.MM2022

Decentralized, not Dehumanized in the Metaverse: Bringing Utility to NFTs through Multimodal Interaction

Anqi Wang, Ze Gao, Lik-Hang Lee +2

User Interaction for NFTs (Non-fungible Tokens) is gaining increasing attention. Although NFTs have been traditionally single-use and monolithic, recent applications aim to connect…

cs.CL2022★ 11 cited

Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models

Ze-Feng Gao, Peiyu Liu, Wayne Xin Zhao +2

Recently, Mixture-of-Experts (short as MoE) architecture has achieved remarkable success in increasing the model capacity of large-scale language models. However, MoE requires inco…

cs.LG2021★ 1 cited

Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

Peiyu Liu, Ze-Feng Gao, Wayne Xin Zhao +3

This paper presents a novel pre-trained language models (PLM) compression approach based on the matrix product operator (short as MPO) from quantum many-body physics. It can decomp…