no code implementations • 6 May 2024 • Nan Xue, Yaping Sun, Zhiyong Chen, Meixia Tao, Xiaodong Xu, Liang Qian, Shuguang Cui, Ping Zhang
In this paper, we propose a wireless distributed LLMs paradigm based on Mixture of Experts (MoE), named WDMoE, deploying LLMs collaboratively across edge servers of base station (BS) and mobile devices in the wireless communications system.
no code implementations • 22 Dec 2023 • Prakash Mallick, Zhiyong Chen
This article proposes an improved trajectory optimization approach for stochastic optimal control of dynamical systems affected by measurement noise by combining optimal control with maximum likelihood techniques to improve the reduction of the cumulative cost-to-go.
no code implementations • 26 Sep 2023 • Shimin Wang, Martin Guay, Zhiyong Chen
An explicit continuous nonlinear mapping was constructed recently in [1] under the assumption that the steady-state generator is linear in the exogenous signal.
no code implementations • 4 Nov 2022 • Zhixin Zhang, Zhiyong Chen
Based on the estimated values of states and faults, a distributed fault tolerance controller is designed to realize asymptotical cooperative cruise control of trains under the dual constraints of ensuring both position difference and velocity difference of adjacent trains in specified ranges throughout the whole process.
no code implementations • 1 Oct 2022 • Chayan Banerjee, Zhiyong Chen, Nasimul Noman
Actor-critic (AC) algorithms are a class of model-free deep reinforcement learning algorithms, which have proven their efficacy in diverse domains, especially in solving continuous control problems.
no code implementations • 2 Sep 2022 • Benshun Yin, Zhiyong Chen, Meixia Tao
In contrast, split learning (SL) can reduce the computing load of devices by using model splitting and assignment, but increase the communication burden to transmit intermediate results.
no code implementations • 15 Jun 2022 • Hassan Dehghani Aghbolagh, Mengbin Ye, Lorenzo Zino, Ming Cao, Zhiyong Chen
Empirical studies suggest a deep intertwining between opinion formation and decision-making processes, but these have been treated as separate problems in the study of dynamical models for social networks.
no code implementations • 24 Sep 2021 • Chayan Banerjee, Zhiyong Chen, Nasimul Noman
It is comparatively more stable and sample efficient when tested on a number of continuous control tasks in MuJoCo environments.
no code implementations • 16 Aug 2021 • Chayan Banerjee, Zhiyong Chen, Nasimul Noman, Mohsen Zamani
Actor-critic (AC) algorithms are known for their efficacy and high performance in solving reinforcement learning problems, but they also suffer from low sampling efficiency.
no code implementations • 13 Aug 2021 • Zhiwei Jia, Shugong Xu, Shiyi Mu, Yue Tao, Shan Cao, Zhiyong Chen
In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation.
no code implementations • 7 May 2021 • Wei Fang, Zhiyong Chen
This paper presents a mathematic dynamic model of a quadrotor unmanned aerial vehicle (QUAV) by using the symbolic regression approach and then proposes a hierarchical control scheme for trajectory tracking.
no code implementations • 5 Mar 2021 • Lili Pan, Peijun Tang, Zhiyong Chen, Zenglin Xu
Disentanglement is defined as the problem of learninga representation that can separate the distinct, informativefactors of variations of data.
no code implementations • 1 Oct 2020 • Prakash Mallick, Zhiyong Chen
Trajectory optimization is a fundamental stochastic optimal control problem.
no code implementations • 24 Mar 2020 • Shimin Wang, Hongwei Zhang, Zhiyong Chen
Distributed adaptive observers are designed for all follower nodes, simultaneously estimate the state and parameters of the leader node.
no code implementations • 12 Aug 2019 • Zhiyong Chen, Zongze Ren, Shugong Xu
Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization.
no code implementations • 6 Aug 2019 • Zongze Ren, Zhiyong Chen, Shugong Xu
The improvements are both based on triplet cause the training stage and the evaluation stage of the baseline x-vector system focus on different aims.
no code implementations • 14 Jun 2018 • Lijun Zhu, Zhiyong Chen, David J. Hill, Shengli Du
Specifically, the closed-loop system is associated with a pair of auxiliary input and output.
Systems and Control