Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Yi Ma

Yi Ma

Massive-MIMO MF Beamforming with or without Grouped STBC for Ultra-Reliable Single-Shot Transmission Using Aged CSIT


Oct 06, 2021
Jinfei Wang, Yi Ma, Na Yi, Rahim Tafazolli, Zhibo Pang

Figure 1 for Massive-MIMO MF Beamforming with or without Grouped STBC for Ultra-Reliable Single-Shot Transmission Using Aged CSIT
Figure 2 for Massive-MIMO MF Beamforming with or without Grouped STBC for Ultra-Reliable Single-Shot Transmission Using Aged CSIT
Figure 3 for Massive-MIMO MF Beamforming with or without Grouped STBC for Ultra-Reliable Single-Shot Transmission Using Aged CSIT
Figure 4 for Massive-MIMO MF Beamforming with or without Grouped STBC for Ultra-Reliable Single-Shot Transmission Using Aged CSIT

  Access Paper or Ask Questions

PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction


Oct 03, 2021
Yi Ma, Kong Aik Lee, Ville Hautamaki, Haizhou Li

Figure 1 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Figure 2 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Figure 3 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Figure 4 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction

  Access Paper or Ask Questions

Hermite Expansion Model and LMMSE Analysis for Low-Resolution Quantized MIMO Detection


Sep 11, 2021
Lifu Liu, Yi Ma, Na Yi

Figure 1 for Hermite Expansion Model and LMMSE Analysis for Low-Resolution Quantized MIMO Detection
Figure 2 for Hermite Expansion Model and LMMSE Analysis for Low-Resolution Quantized MIMO Detection
Figure 3 for Hermite Expansion Model and LMMSE Analysis for Low-Resolution Quantized MIMO Detection
Figure 4 for Hermite Expansion Model and LMMSE Analysis for Low-Resolution Quantized MIMO Detection
* IEEE Trans. Signal Processing 2021 
 * 16 pages 
  Access Paper or Ask Questions

A Non-Stationary Channel Model with Correlated NLoS/LoS States for ELAA-mMIMO


Aug 18, 2021
Jiuyu Liu, Yi Ma, Jinfei Wang, Na Yi, Songyan Xue, Rahim Tafazolli, Fan Wang

Figure 1 for A Non-Stationary Channel Model with Correlated NLoS/LoS States for ELAA-mMIMO
Figure 2 for A Non-Stationary Channel Model with Correlated NLoS/LoS States for ELAA-mMIMO
Figure 3 for A Non-Stationary Channel Model with Correlated NLoS/LoS States for ELAA-mMIMO
Figure 4 for A Non-Stationary Channel Model with Correlated NLoS/LoS States for ELAA-mMIMO

  Access Paper or Ask Questions

Computational Benefits of Intermediate Rewards for Hierarchical Planning


Jul 08, 2021
Yuexiang Zhai, Christina Baek, Zhengyuan Zhou, Jiantao Jiao, Yi Ma

Figure 1 for Computational Benefits of Intermediate Rewards for Hierarchical Planning
Figure 2 for Computational Benefits of Intermediate Rewards for Hierarchical Planning
Figure 3 for Computational Benefits of Intermediate Rewards for Hierarchical Planning
Figure 4 for Computational Benefits of Intermediate Rewards for Hierarchical Planning

  Access Paper or Ask Questions

On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging


Jun 30, 2021
Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan

Figure 1 for On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging
Figure 2 for On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging
Figure 3 for On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging
Figure 4 for On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging

  Access Paper or Ask Questions

Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching


Jun 18, 2021
Jiabao Lei, Kui Jia, Yi Ma

Figure 1 for Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching
Figure 2 for Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching
Figure 3 for Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching
Figure 4 for Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching
* arXiv admin note: text overlap with arXiv:2002.06597 
  Access Paper or Ask Questions

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction


Jun 10, 2021
Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

Figure 1 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
Figure 2 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
Figure 3 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
Figure 4 for ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
* This paper integrates previous two manuscripts: arXiv:2006.08558 and arXiv:2010.14765, with significantly improved organization, presentation, and new results; V2 polishes writing and adds citation 
  Access Paper or Ask Questions

End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels


May 04, 2021
Songyan Xue, Yi Ma, Na Yi

Figure 1 for End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels
Figure 2 for End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels
Figure 3 for End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels
Figure 4 for End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channels
* 26 pages, 14 figures, transaction 
  Access Paper or Ask Questions

Fully Convolutional Line Parsing


Apr 23, 2021
Xili Dai, Xiaojun Yuan, Haigang Gong, Yi Ma

Figure 1 for Fully Convolutional Line Parsing
Figure 2 for Fully Convolutional Line Parsing
Figure 3 for Fully Convolutional Line Parsing
Figure 4 for Fully Convolutional Line Parsing
* 10 pages 
  Access Paper or Ask Questions

NeRD: Neural 3D Reflection Symmetry Detector


Apr 19, 2021
Yichao Zhou, Shichen Liu, Yi Ma

Figure 1 for NeRD: Neural 3D Reflection Symmetry Detector
Figure 2 for NeRD: Neural 3D Reflection Symmetry Detector
Figure 3 for NeRD: Neural 3D Reflection Symmetry Detector
Figure 4 for NeRD: Neural 3D Reflection Symmetry Detector
* CVPR 2021. overlaps with arXiv:2006.10042 
  Access Paper or Ask Questions

Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image


Apr 16, 2021
Cheng Yang, Jia Zheng, Xili Dai, Rui Tang, Yi Ma, Xiaojun Yuan

Figure 1 for Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
Figure 2 for Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
Figure 3 for Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
Figure 4 for Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
* Code is available at https://github.com/Cyang0515/NonCuboidRoom 
  Access Paper or Ask Questions

Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition


Mar 17, 2021
Yaodong Yu, Zitong Yang, Edgar Dobriban, Jacob Steinhardt, Yi Ma

Figure 1 for Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition
Figure 2 for Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition
Figure 3 for Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition
Figure 4 for Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition

  Access Paper or Ask Questions

Incremental Learning via Rate Reduction


Nov 30, 2020
Ziyang Wu, Christina Baek, Chong You, Yi Ma

Figure 1 for Incremental Learning via Rate Reduction
Figure 2 for Incremental Learning via Rate Reduction
Figure 3 for Incremental Learning via Rate Reduction
Figure 4 for Incremental Learning via Rate Reduction

  Access Paper or Ask Questions

Deep Networks from the Principle of Rate Reduction


Oct 27, 2020
Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

Figure 1 for Deep Networks from the Principle of Rate Reduction
Figure 2 for Deep Networks from the Principle of Rate Reduction
Figure 3 for Deep Networks from the Principle of Rate Reduction
Figure 4 for Deep Networks from the Principle of Rate Reduction

  Access Paper or Ask Questions

Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients


Sep 28, 2020
Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao

Figure 1 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Figure 2 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Figure 3 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Figure 4 for Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
* 16 pages 
  Access Paper or Ask Questions

HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures


Aug 07, 2020
Yichao Zhou, Jingwei Huang, Xili Dai, Linjie Luo, Zhili Chen, Yi Ma

Figure 1 for HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures
Figure 2 for HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures
Figure 3 for HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures
Figure 4 for HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures

  Access Paper or Ask Questions

Learning Long-term Visual Dynamics with Region Proposal Interaction Networks


Aug 05, 2020
Haozhi Qi, Xiaolong Wang, Deepak Pathak, Yi Ma, Jitendra Malik

Figure 1 for Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
Figure 2 for Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
Figure 3 for Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
Figure 4 for Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
* Code: https://github.com/HaozhiQi/RPIN; Website: https://haozhiqi.github.io/RPIN/ 
  Access Paper or Ask Questions

Learning to Parse Wireframes in Images of Man-Made Environments


Jul 15, 2020
Kun Huang, Yifan Wang, Zihan Zhou, Tianjiao Ding, Shenghua Gao, Yi Ma

Figure 1 for Learning to Parse Wireframes in Images of Man-Made Environments
Figure 2 for Learning to Parse Wireframes in Images of Man-Made Environments
Figure 3 for Learning to Parse Wireframes in Images of Man-Made Environments
Figure 4 for Learning to Parse Wireframes in Images of Man-Made Environments
* IEEE Conference on Computer Vision and Pattern Recognition (2018) 626-635 
 * CVPR 2018 
  Access Paper or Ask Questions

Deep Isometric Learning for Visual Recognition


Jun 30, 2020
Haozhi Qi, Chong You, Xiaolong Wang, Yi Ma, Jitendra Malik

Figure 1 for Deep Isometric Learning for Visual Recognition
Figure 2 for Deep Isometric Learning for Visual Recognition
Figure 3 for Deep Isometric Learning for Visual Recognition
Figure 4 for Deep Isometric Learning for Visual Recognition
* ICML 2020; Code: https://github.com/HaozhiQi/ISONet 
  Access Paper or Ask Questions

Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising


Jun 29, 2020
Xiaotian Hao, Zhaoqing Peng, Yi Ma, Guan Wang, Junqi Jin, Jianye Hao, Shan Chen, Rongquan Bai, Mingzhou Xie, Miao Xu, Zhenzhe Zheng, Chuan Yu, Han Li, Jian Xu, Kun Gai

Figure 1 for Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
Figure 2 for Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
Figure 3 for Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
Figure 4 for Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
* accepted by ICML 2020 
  Access Paper or Ask Questions

Stochastic Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization


Jun 27, 2020
Chaobing Song, Yong Jiang, Yi Ma

Figure 1 for Stochastic Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization
Figure 2 for Stochastic Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization
Figure 3 for Stochastic Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization
* 22 pages, 12 figures 
  Access Paper or Ask Questions

Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction


Jun 17, 2020
Yichao Zhou, Shichen Liu, Yi Ma

Figure 1 for Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction
Figure 2 for Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction
Figure 3 for Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction
Figure 4 for Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction

  Access Paper or Ask Questions

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization


Jun 16, 2020
Chong You, Zhihui Zhu, Qing Qu, Yi Ma

Figure 1 for Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
Figure 2 for Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
Figure 3 for Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
Figure 4 for Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

  Access Paper or Ask Questions

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction


Jun 15, 2020
Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song, Yi Ma

Figure 1 for Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
Figure 2 for Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
Figure 3 for Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
Figure 4 for Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

  Access Paper or Ask Questions

Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising


May 12, 2020
Xiaotian Hao, Junqi Jin, Jianye Hao, Jin Li, Weixun Wang, Yi Ma, Zhenzhe Zheng, Han Li, Jian Xu, Kun Gai

Figure 1 for Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising
Figure 2 for Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising
Figure 3 for Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising
Figure 4 for Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising
* accepted by IJCAI 2020 
  Access Paper or Ask Questions

On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MU-MIMO Systems


Apr 14, 2020
Songyan Xue, Yi Ma, Na Yi, Rahim Tafazolli

Figure 1 for On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MU-MIMO Systems
Figure 2 for On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MU-MIMO Systems
Figure 3 for On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MU-MIMO Systems
Figure 4 for On Deep Learning Solutions for Joint Transmitter and Noncoherent Receiver Design in MU-MIMO Systems
* 6 pages, 4 figures 
  Access Paper or Ask Questions

A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection


Apr 01, 2020
Songyan Xue, Yi Ma, Na Yi, Terence E. Dodgson

Figure 1 for A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection
Figure 2 for A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection
Figure 3 for A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection
Figure 4 for A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection
* 12 pages, 11 figures, transcation on communications 
  Access Paper or Ask Questions