activity
20222024
most citedTake the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization

3 citations · 8 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG20243 cited

Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization

Xuxi Chen, Zhendong Wang, Daouda Sow +5

In the rapidly advancing arena of large language models (LLMs), a key challenge is to enhance their capabilities amid a looming shortage of high-quality training data. Our study st…

cs.LG20232 cited

MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting

Xing Wang, Zhendong Wang, Kexin Yang +4

Long-term time series forecasting plays an important role in various real-world scenarios. Recent deep learning methods for long-term series forecasting tend to capture the intrica…

cs.SE2023

Optimizing Workflow for Elite Developers: Perspectives on Leveraging SE Bots

Zhendong Wang, Yi Wang, David Redmiles

Small-scale automation services in Software Engineering, known as SE Bots, have gradually infiltrated every aspect of daily software development with the goal of enhancing producti…

eess.SP2023

Collaborative Multi-BS Power Management for Dense Radio Access Network using Deep Reinforcement Learning

Yuchao Chang, Wen Chen, Jun Li +4

Network energy efficiency is a main pillar in the design and operation of wireless communication systems. In this paper, we investigate a dense radio access network (dense-RAN) cap…

cs.NI20231 cited

Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction

Xing Wang, Kexin Yang, Zhendong Wang +4

Cellular traffic prediction is an indispensable part for intelligent telecommunication networks. Nevertheless, due to the frequent user mobility and complex network scheduling mech…

cs.CR20222 cited

Demystifying Arch-hints for Model Extraction: An Attack in Unified Memory System

Zhendong Wang, Xiaoming Zeng, Xulong Tang +3

The deep neural network (DNN) models are deemed confidential due to their unique value in expensive training efforts, privacy-sensitive training data, and proprietary network chara…