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 Bo Li

Bo Li

*co-first authors

Trustworthy AI: From Principles to Practices


Oct 04, 2021
Bo Li, Peng Qi, Bo Liu, Shuai Di, Jingen Liu, Jiquan Pei, Jinfeng Yi, Bowen Zhou

Figure 1 for Trustworthy AI: From Principles to Practices
Figure 2 for Trustworthy AI: From Principles to Practices
Figure 3 for Trustworthy AI: From Principles to Practices
Figure 4 for Trustworthy AI: From Principles to Practices

  Access Paper or Ask Questions

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition


Oct 01, 2021
Yu Zhang, Daniel S. Park, Wei Han, James Qin, Anmol Gulati, Joel Shor, Aren Jansen, Yuanzhong Xu, Yanping Huang, Shibo Wang, Zongwei Zhou, Bo Li, Min Ma, William Chan, Jiahui Yu, Yongqiang Wang, Liangliang Cao, Khe Chai Sim, Bhuvana Ramabhadran, Tara N. Sainath, Françoise Beaufays, Zhifeng Chen, Quoc V. Le, Chung-Cheng Chiu, Ruoming Pang, Yonghui Wu

Figure 1 for BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
Figure 2 for BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
Figure 3 for BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
Figure 4 for BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
* 14 pages, 7 figures, 13 tables; v2: minor corrections, reference baselines and bibliography updated 
  Access Paper or Ask Questions

Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence


Sep 28, 2021
Wennan Chang, Pengtao Dang, Changlin Wan, Xiaoyu Lu, Yue Fang, Tong Zhao, Yong Zang, Bo Li, Chi Zhang, Sha Cao

Figure 1 for Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence
Figure 2 for Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence
* Accepted by ICDM IEEE 2021 
  Access Paper or Ask Questions

DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions


Sep 27, 2021
Jonathan S. Kent, Bo Li

Figure 1 for DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
Figure 2 for DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
Figure 3 for DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
Figure 4 for DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
* 20 pages, 8 figures, Undergraduate Thesis 
  Access Paper or Ask Questions

Eliciting Information with Partial Signals in Repeated Games


Sep 09, 2021
Yutong Wu, Ali Khodabakhsh, Bo Li, Evdokia Nikolova, Emmanouil Pountourakis

Figure 1 for Eliciting Information with Partial Signals in Repeated Games
Figure 2 for Eliciting Information with Partial Signals in Repeated Games
Figure 3 for Eliciting Information with Partial Signals in Repeated Games
Figure 4 for Eliciting Information with Partial Signals in Repeated Games
* 24 pages, 4 figures 
  Access Paper or Ask Questions

Disentangled High Quality Salient Object Detection


Sep 02, 2021
Lv Tang, Bo Li, Shouhong Ding, Mofei Song

Figure 1 for Disentangled High Quality Salient Object Detection
Figure 2 for Disentangled High Quality Salient Object Detection
Figure 3 for Disentangled High Quality Salient Object Detection
Figure 4 for Disentangled High Quality Salient Object Detection
* Full version of ICCV2021 
  Access Paper or Ask Questions

Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision


Aug 30, 2021
Bo Li, Xinyang Jiang, Donglin Bai, Yuge Zhang, Ningxin Zheng, Xuanyi Dong, Lu Liu, Yuqing Yang, Dongsheng Li

Figure 1 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
Figure 2 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
Figure 3 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
Figure 4 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
* ArXiv Preprint 
  Access Paper or Ask Questions

LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis


Aug 20, 2021
Fan Wu, Yunhui Long, Ce Zhang, Bo Li

Figure 1 for LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis
Figure 2 for LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis
Figure 3 for LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis
Figure 4 for LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis

  Access Paper or Ask Questions

Energy-Based Open-World Uncertainty Modeling for Confidence Calibration


Aug 16, 2021
Yezhen Wang, Bo Li, Tong Che, Kaiyang Zhou, Ziwei Liu, Dongsheng Li

Figure 1 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Figure 2 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Figure 3 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Figure 4 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
* ICCV 2021 (Poster) 
  Access Paper or Ask Questions

On the Certified Robustness for Ensemble Models and Beyond


Jul 22, 2021
Zhuolin Yang, Linyi Li, Xiaojun Xu, Bhavya Kailkhura, Tao Xie, Bo Li

Figure 1 for On the Certified Robustness for Ensemble Models and Beyond
Figure 2 for On the Certified Robustness for Ensemble Models and Beyond
Figure 3 for On the Certified Robustness for Ensemble Models and Beyond
Figure 4 for On the Certified Robustness for Ensemble Models and Beyond
* 57 pages, 11 pages for main text 
  Access Paper or Ask Questions

Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks


Jul 14, 2021
Shaohuai Shi, Lin Zhang, Bo Li

Figure 1 for Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks
Figure 2 for Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks
Figure 3 for Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks
Figure 4 for Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks
* 11 pages. Accepted to IEEE ICDCS 2021 
  Access Paper or Ask Questions

Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition


Jul 13, 2021
Junkun Yuan, Anpeng Wu, Kun Kuang, Bo Li, Runze Wu, Fei Wu, Lanfen Lin

Figure 1 for Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition
Figure 2 for Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition
Figure 3 for Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition
Figure 4 for Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition
* 12 pages 
  Access Paper or Ask Questions

Distributionally Robust Learning with Stable Adversarial Training


Jun 30, 2021
Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li

Figure 1 for Distributionally Robust Learning with Stable Adversarial Training
Figure 2 for Distributionally Robust Learning with Stable Adversarial Training
Figure 3 for Distributionally Robust Learning with Stable Adversarial Training
Figure 4 for Distributionally Robust Learning with Stable Adversarial Training
* arXiv admin note: substantial text overlap with arXiv:2006.04414 
  Access Paper or Ask Questions

Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis


Jun 28, 2021
Xianjing Liu, Bo Li, Esther Bron, Wiro Niessen, Eppo Wolvius, Gennady Roshchupkin

Figure 1 for Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis
Figure 2 for Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis
Figure 3 for Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis
Figure 4 for Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis
* Accepted at MICCAI 2021 
  Access Paper or Ask Questions

A Comprehensive Survey of Incentive Mechanism for Federated Learning


Jun 27, 2021
Rongfei Zeng, Chao Zeng, Xingwei Wang, Bo Li, Xiaowen Chu

Figure 1 for A Comprehensive Survey of Incentive Mechanism for Federated Learning
Figure 2 for A Comprehensive Survey of Incentive Mechanism for Federated Learning
Figure 3 for A Comprehensive Survey of Incentive Mechanism for Federated Learning
Figure 4 for A Comprehensive Survey of Incentive Mechanism for Federated Learning
* more than 10 pages 
  Access Paper or Ask Questions

MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning


Jun 24, 2021
Chen Liu, Bo Li, Jun Zhao, Ming Su, Xu-Dong Liu

Figure 1 for MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
Figure 2 for MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
Figure 3 for MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
Figure 4 for MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
* 8 pages, 7 figures, Accepted at the 30th International Joint Conference on Artificial Intelligence(IJCAI 2021) 
  Access Paper or Ask Questions

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing


Jun 17, 2021
Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li

Figure 1 for CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
Figure 2 for CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
Figure 3 for CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
Figure 4 for CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
* 25 pages, 7 figures 
  Access Paper or Ask Questions

Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks


Jun 17, 2021
Yulong Cao*, Ningfei Wang*, Chaowei Xiao*, Dawei Yang*, Jin Fang, Ruigang Yang, Qi Alfred Chen, Mingyan Liu, Bo Li

Figure 1 for Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
Figure 2 for Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
Figure 3 for Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
Figure 4 for Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
* Accepted by IEEE S&P 2021 
  Access Paper or Ask Questions

Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation


Jun 16, 2021
Haoxiang Wang, Han Zhao, Bo Li

Figure 1 for Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Figure 2 for Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Figure 3 for Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Figure 4 for Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
* ICML 2021 camera-ready version. Code is released at https://github.com/AI-secure/multi-task-learning 
  Access Paper or Ask Questions

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks


Jun 15, 2021
Chulin Xie, Minghao Chen, Pin-Yu Chen, Bo Li

Figure 1 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Figure 2 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Figure 3 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Figure 4 for CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
* ICML 2021 
  Access Paper or Ask Questions

Invariant Information Bottleneck for Domain Generalization


Jun 14, 2021
Bo Li, Yifei Shen, Yezhen Wang, Wenzhen Zhu, Colorado J. Reed, Jun Zhang, Dongsheng Li, Kurt Keutzer, Han Zhao

Figure 1 for Invariant Information Bottleneck for Domain Generalization
Figure 2 for Invariant Information Bottleneck for Domain Generalization
Figure 3 for Invariant Information Bottleneck for Domain Generalization
Figure 4 for Invariant Information Bottleneck for Domain Generalization
* The work is in progress 
  Access Paper or Ask Questions

Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks


Jun 11, 2021
Nezihe Merve Gürel, Xiangyu Qi, Luka Rimanic, Ce Zhang, Bo Li

Figure 1 for Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
Figure 2 for Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
Figure 3 for Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
Figure 4 for Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
* International Conference on Machine Learning 2021, 37 pages, 8 figures, 9 tables 
  Access Paper or Ask Questions

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation


Jun 10, 2021
Jiawei Zhang, Linyi Li, Huichen Li, Xiaolu Zhang, Shuang Yang, Bo Li

Figure 1 for Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
Figure 2 for Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
Figure 3 for Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
Figure 4 for Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
* ICML 2021 
  Access Paper or Ask Questions