activity
20192023
most citedMulti-Task Deep Neural Networks for Natural Language Understanding

221 citations · 540 across the 12 of their papers we have counts for

collaborators

15 papers

cs.CL202213 cited

Momentum Calibration for Text Generation

Xingxing Zhang, Yiran Liu, Xun Wang +5

The input and output of most text generation tasks can be transformed to two sequences of tokens and they can be modeled using sequence-to-sequence learning modeling tools such as…

cs.CL20229 cited

HyperTuning: Toward Adapting Large Language Models without Back-propagation

Jason Phang, Yi Mao, Pengcheng He +1

Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require full gradient-based o…

cs.CL20222 cited

MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation

Simiao Zuo, Qingru Zhang, Chen Liang +3

Pre-trained language models have demonstrated superior performance in various natural language processing tasks. However, these models usually contain hundreds of millions of param…

cs.CL2022

CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing

Chen Liang, Pengcheng He, Yelong Shen +2

Model ensemble is a popular approach to produce a low-variance and well-generalized model. However, it induces large memory and inference costs, which are often not affordable for…

cs.CV20226 cited

Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs

Huangjie Zheng, Pengcheng He, Weizhu Chen +1

Token-mixing multi-layer perceptron (MLP) models have shown competitive performance in computer vision tasks with a simple architecture and relatively small computational cost. The…

cs.CL20228 cited

No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models

Chen Liang, Haoming Jiang, Simiao Zuo +5

Recent research has shown the existence of significant redundancy in large Transformer models. One can prune the redundant parameters without significantly sacrificing the generali…