Search Results for author: Xiaoyu Chen

Found 40 papers, 6 papers with code

HW-TSC’s Submissions to the WMT21 Biomedical Translation Task

no code implementations WMT (EMNLP) 2021 Hao Yang, Zhanglin Wu, Zhengzhe Yu, Xiaoyu Chen, Daimeng Wei, Zongyao Li, Hengchao Shang, Minghan Wang, Jiaxin Guo, Lizhi Lei, Chuanfei Xu, Min Zhang, Ying Qin

This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).

Translation

Flow-based Recurrent Belief State Learning for POMDPs

no code implementations23 May 2022 Xiaoyu Chen, Yao Mu, Ping Luo, Shengbo Li, Jianyu Chen

Furthermore, we show that the learned belief states can be plugged into downstream RL algorithms to improve performance.

Decision Making Variational Inference

Distributional Reinforcement Learning for Multi-Dimensional Reward Functions

no code implementations NeurIPS 2021 Pushi Zhang, Xiaoyu Chen, Li Zhao, Wei Xiong, Tao Qin, Tie-Yan Liu

To fully inherit the benefits of distributional RL and hybrid reward architectures, we introduce Multi-Dimensional Distributional DQN (MD3QN), which extends distributional RL to model the joint return distribution from multiple reward sources.

Distributional Reinforcement Learning reinforcement-learning

Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver

no code implementations ICLR 2022 Xiaoyu Chen, Jiachen Hu, Lin F. Yang, LiWei Wang

In particular, we take a plug-in solver approach, where we focus on learning a model in the exploration phase and demand that \emph{any planning algorithm} on the learned model can give a near-optimal policy.

Model-based Reinforcement Learning

WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition

1 code implementation7 Oct 2021 BinBin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, Di wu, Zhendong Peng

In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total.

Optical Character Recognition Speech Recognition +1

The $f$-Divergence Reinforcement Learning Framework

no code implementations24 Sep 2021 Chen Gong, Qiang He, Yunpeng Bai, Zhou Yang, Xiaoyu Chen, Xinwen Hou, Xianjie Zhang, Yu Liu, Guoliang Fan

In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards.

Decision Making Mathematical Proofs +1

MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning

no code implementations22 Sep 2021 Qiang He, Chen Gong, Yuxun Qu, Xiaoyu Chen, Xinwen Hou, Yu Liu

Ensemble reinforcement learning (RL) aims to mitigate instability in Q-learning and to learn a robust policy, which introduces multiple value and policy functions.

Q-Learning reinforcement-learning

LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders

no code implementations22 Sep 2021 Xiaoyu Chen, Chen Gong, Qiang He, Xinwen Hou, Yu Liu

Variational autoencoders (VAEs), as an important aspect of generative models, have received a lot of research interests and reached many successful applications.

Image Generation

Adaptively Weighted Top-N Recommendation for Organ Matching

no code implementations23 Jul 2021 Parshin Shojaee, Xiaoyu Chen, Ran Jin

Because of the shortage, organ matching decision is the most critical decision to assign the limited viable organs to the most suitable patients.

Decision Making

Certifiably Robust Interpretation via Renyi Differential Privacy

no code implementations4 Jul 2021 Ao Liu, Xiaoyu Chen, Sijia Liu, Lirong Xia, Chuang Gan

The advantages of our Renyi-Robust-Smooth (RDP-based interpretation method) are three-folds.

U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition

no code implementations10 Jun 2021 Di wu, BinBin Zhang, Chao Yang, Zhendong Peng, Wenjing Xia, Xiaoyu Chen, Xin Lei

On the experiment of AISHELL-1, we achieve a 4. 63\% character error rate (CER) with a non-streaming setup and 5. 05\% with a streaming setup with 320ms latency by U2++.

Data Augmentation Speech Recognition

Friedel Oscillations of Vortex Bound States Under Extreme Quantum Limit in KCa2Fe4As4F2

no code implementations24 Feb 2021 Xiaoyu Chen, Wen Duan, Xinwei Fan, Wenshan Hong, Kailun Chen, Huan Yang, Shiliang Li, Huiqian Luo, Hai-Hu Wen

We report the observation of discrete vortex bound states with the energy levels deviating from the widely believed ratio of 1:3:5 in the vortices of an iron based superconductor KCa2Fe4As4F2 through scanning tunneling microcopy (STM).

Superconductivity Strongly Correlated Electrons

Single particle tunneling spectroscopy and superconducting gaps in layered iron based superconductor KCa$_{2}$Fe$_{4}$As$_{4}$F$_{2}$

no code implementations17 Feb 2021 Wen Duan, Kailun Chen, Wenshan Hong, Xiaoyu Chen, Huan Yang, Shiliang Li, Huiqian Luo, Hai-Hu Wen

On the second type of surface which is rarely obtained, the fully gapped feature can still be observed on the tunneling spectra, although multiple gaps are obtained either from a single spectrum or separate ones, and the gap values determined from coherence peaks locate mainly in the range from 4 to 8 meV.

Superconductivity

Near-optimal Representation Learning for Linear Bandits and Linear RL

no code implementations8 Feb 2021 Jiachen Hu, Xiaoyu Chen, Chi Jin, Lihong Li, LiWei Wang

This paper studies representation learning for multi-task linear bandits and multi-task episodic RL with linear value function approximation.

Representation Learning

WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

3 code implementations2 Feb 2021 Zhuoyuan Yao, Di wu, Xiong Wang, BinBin Zhang, Fan Yu, Chao Yang, Zhendong Peng, Xiaoyu Chen, Lei Xie, Xin Lei

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.

Speech Recognition

Modeling Method for the Coupling Relations of Microgrid Cyber-Physical Systems Driven by Hybrid Spatiotemporal Events

no code implementations1 Feb 2021 Xiaoyong Bo, Xiaoyu Chen, Huashun Li, Yunchang Dong, Zhaoyang Qu, Lei Wang, Yang Li

Considering the constraints of the temporal conversion of information flow and energy flow, a microgrid CPS coupling model is established, the effectiveness of which is verified by simulating false data injection attack (FDIA) scenarios.

Decision Making

Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation

no code implementations28 Dec 2020 Xiaoyu Chen, Chi Zhang, Guosheng Lin, Jing Han

Moreover, when we use our network to handle the long-tail problem in a fully supervised point cloud segmentation dataset, it can also effectively boost the performance of the few-shot classes.

Few-Shot Learning Point Cloud Segmentation +1

Relation Extraction with Contextualized Relation Embedding (CRE)

1 code implementation EMNLP (DeeLIO) 2020 Xiaoyu Chen, Rohan Badlani

This paper proposes an architecture for the relation extraction task that integrates semantic information with knowledge base modeling in a novel manner.

Entity Embeddings Relation Extraction

Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL

no code implementations ICLR 2021 Xiaoyu Chen, Jiachen Hu, Lihong Li, Li-Wei Wang

The regret of FMDP-BF is shown to be exponentially smaller than that of optimal algorithms designed for non-factored MDPs, and improves on the best previous result for FMDPs~\citep{osband2014near} by a factored of $\sqrt{H|\mathcal{S}_i|}$, where $|\mathcal{S}_i|$ is the cardinality of the factored state subspace and $H$ is the planning horizon.

reinforcement-learning

Noisy Agents: Self-supervised Exploration by Predicting Auditory Events

no code implementations27 Jul 2020 Chuang Gan, Xiaoyu Chen, Phillip Isola, Antonio Torralba, Joshua B. Tenenbaum

Humans integrate multiple sensory modalities (e. g. visual and audio) to build a causal understanding of the physical world.

Atari Games

(Locally) Differentially Private Combinatorial Semi-Bandits

no code implementations ICML 2020 Xiaoyu Chen, Kai Zheng, Zixin Zhou, Yunchang Yang, Wei Chen, Li-Wei Wang

In this paper, we study Combinatorial Semi-Bandits (CSB) that is an extension of classic Multi-Armed Bandits (MAB) under Differential Privacy (DP) and stronger Local Differential Privacy (LDP) setting.

Multi-Armed Bandits Privacy Preserving

Non-destructive three-dimensional measurement of hand vein based on self-supervised network

no code implementations29 Jun 2019 Xiaoyu Chen, Qixin Wang, Jinzhou Ge, Yi Zhang, Jing Han

At present, supervised stereo methods based on deep neural network have achieved impressive results.

High Sensitivity Snapshot Spectrometer Based on Deep Network Unmixing

no code implementations29 Jun 2019 XiaoYu Chen, Xu Wang, Lianfa Bai, Jing Han, Zhuang Zhao

In this paper, we present a convolution neural network based method to recover the light intensity distribution from the overlapped dispersive spectra instead of adding an extra light path to capture it directly for the first time.

Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication

no code implementations ICLR 2020 Yuanhao Wang, Jiachen Hu, Xiaoyu Chen, Li-Wei Wang

We study the problem of regret minimization for distributed bandits learning, in which $M$ agents work collaboratively to minimize their total regret under the coordination of a central server.

Multi-Armed Bandits

Passive TCP Identification for Wired and WirelessNetworks: A Long-Short Term Memory Approach

no code implementations9 Apr 2019 Xiaoyu Chen, Shugong Xu, Xudong Chen, Shan Cao, Shunqing Zhang, Yanzan Sun

TCP congestion control algorithm identification (TCP identification) can be used to significantly improve network efficiency.

Residual Pyramid Learning for Single-Shot Semantic Segmentation

1 code implementation23 Mar 2019 Xiaoyu Chen, Xiaotian Lou, Lianfa Bai, Jing Han

In this paper, we put forward a method for single-shot segmentation in a feature residual pyramid network (RPNet), which learns the main and residuals of segmentation by decomposing the label at different levels of residual blocks.

Semantic Segmentation

Discrete Potts Model for Generating Superpixels on Noisy Images

no code implementations20 Mar 2018 Ruobing Shen, Xiaoyu Chen, Xiangrui Zheng, Gerhard Reinelt

Many computer vision applications, such as object recognition and segmentation, increasingly build on superpixels.

BSDS500 Denoising +2

The Spaces of Data, Information, and Knowledge

no code implementations6 Nov 2014 Xiaoyu Chen, Dongming Wang

We study the data space $D$ of any given data set $X$ and explain how functions and relations are defined over $D$.

Automated Generation of Geometric Theorems from Images of Diagrams

no code implementations6 Jun 2014 Xiaoyu Chen, Dan Song, Dongming Wang

We propose an approach to generate geometric theorems from electronic images of diagrams automatically.

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