Search Results for author: Xin Cheng

Found 19 papers, 6 papers with code

An ADMM-Based Geometric Configuration Optimization in RSSD-Based Source Localization By UAVs with Spread Angle Constraint

no code implementations24 Nov 2023 Xin Cheng, Weiqiang Zhu, Feng Shu, Jiangzhou Wang

Deploying multiple unmanned aerial vehicles (UAVs) to locate a signal-emitting source covers a wide range of military and civilian applications like rescue and target tracking.

SCALE: Synergized Collaboration of Asymmetric Language Translation Engines

1 code implementation29 Sep 2023 Xin Cheng, Xun Wang, Tao Ge, Si-Qing Chen, Furu Wei, Dongyan Zhao, Rui Yan

In this paper, we introduce SCALE, a collaborative framework that connects compact Specialized Translation Models (STMs) and general-purpose Large Language Models (LLMs) as one unified translation engine.

Continual Learning Translation

Weakly Supervised Regression with Interval Targets

no code implementations18 Jun 2023 Xin Cheng, Yuzhou Cao, Ximing Li, Bo An, Lei Feng

Third, we propose a statistically consistent limiting method for RIT to train the model by limiting the predictions to the interval.


Partial-Label Regression

1 code implementation AAAI 2023 Xin Cheng, Deng-Bao Wang, Lei Feng, Min-Ling Zhang, Bo An

Our proposed methods are theoretically grounded and can be compatible with any models, optimizers, and losses.

Partial Label Learning regression +1

Decouple knowledge from parameters for plug-and-play language modeling

1 code implementation19 May 2023 Xin Cheng, Yankai Lin, Xiuying Chen, Dongyan Zhao, Rui Yan

The key intuition is to decouple the knowledge storage from model parameters with an editable and scalable key-value memory and leverage knowledge in an explainable manner by knowledge retrieval in the DPM.

Domain Adaptation Language Modelling +1

A Topic-aware Summarization Framework with Different Modal Side Information

no code implementations19 May 2023 Xiuying Chen, Mingzhe Li, Shen Gao, Xin Cheng, Qiang Yang, Qishen Zhang, Xin Gao, Xiangliang Zhang

To address these two challenges, we first propose a unified topic encoder, which jointly discovers latent topics from the document and various kinds of side information.

Contrastive Learning

Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory

1 code implementation3 May 2023 Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu, Dongyan Zhao, Rui Yan

In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a novel framework, selfmem, which addresses this limitation by iteratively employing a retrieval-augmented generator to create an unbounded memory pool and using a memory selector to choose one output as memory for the subsequent generation round.

Abstractive Text Summarization Dialogue Generation +2

Neural Machine Translation with Contrastive Translation Memories

1 code implementation6 Dec 2022 Xin Cheng, Shen Gao, Lemao Liu, Dongyan Zhao, Rui Yan

Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios.

Contrastive Learning Machine Translation +3

Optimal Measurement of Drone Swarm in RSS-based Passive Localization with Region Constraints

no code implementations2 Aug 2022 Xin Cheng, Feng Shu, YiFan Li, Zhihong Zhuang, Di wu, Jiangzhou Wang

In this paper, optimal geometrical configurations of UAVs in received signal strength (RSS)-based localization under region constraints are investigated.

Providing Location Information at Edge Networks: A Federated Learning-Based Approach

no code implementations17 May 2022 Xin Cheng, Tingting Liu, Feng Shu, Chuan Ma, Jun Li, Jiangzhou Wang

Recently, the development of mobile edge computing has enabled exhilarating edge artificial intelligence (AI) with fast response and low communication cost.

Edge-computing Federated Learning +1

Rapid Phase Ambiguity Elimination Methods for DOA Estimator via Hybrid Massive MIMO Receive Array

no code implementations27 Apr 2022 Xichao Zhan, YiWen Chen, Feng Shu, Xin Cheng, Yuanyuan Wu, Qi Zhang, Yifang Li, Peng Zhang

In the proposed Max-RP-QI, a quadratic interpolation scheme is adopted to interpolate the three DOA values corresponding to the largest three receive powers of Max-RP.

Two Low-complexity DOA Estimators for Massive/Ultra-massive MIMO Receive Array

no code implementations20 Apr 2022 YiWen Chen, Xichao Zhan, Feng Shu, Qijuan Jie, Xin Cheng, Zhihong Zhuang, Jiangzhou Wang

Eigen-decomposition-based direction finding methods of using large-scale/ultra-large-scale fully-digital receive antenna arrays lead to a high or ultra-high complexity.

Federated Learning-Based Localization with Heterogeneous Fingerprint Database

no code implementations29 Mar 2022 Xin Cheng, Chuan Ma, Jun Li, Haiwei Song, Feng Shu, Jiangzhou Wang

Fingerprint-based localization plays an important role in indoor location-based services, where the position information is usually collected in distributed clients and gathered in a centralized server.

Federated Learning

Communication-efficient Coordinated RSS-based Distributed Passive Localization via Drone Cluster

no code implementations1 Apr 2021 Xin Cheng, Weiping Shi, Wenlong Cai, Weiqiang Zhu, Tong Shen, Feng Shu, Jiangzhou Wang

Simulation results show that the proposed DMM performs better than the existing distributed Gauss-Newton method (DGN) in terms of root of mean square error (RMSE) under a limited low communication overhead constraint.

Enhanced RSS-based UAV Localization via Trajectory and Multi-base Stations

no code implementations3 Nov 2020 YiFan Li, Feng Shu, Baihua Shi, Xin Cheng, Yaoliang Song, Jiangzhou Wang

First, fixing the nth BS, by exploiting multiple measurements along trajectory, the position of UAV is computed by ML rule.

Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices

no code implementations5 Jun 2020 Xin Cheng, Lei Zhang, Yin Tang, Yue Liu, Hao Wu, Jun He

For deep learning, improvements in performance have to heavily rely on increasing model size or capacity to scale to larger and larger datasets, which inevitably leads to the increase of operations.

Human Activity Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.