Zhenguo Li Director, AI Theory Lab Principal Researcher, Noah's Ark Lab Huawei Technologies E-mail: zhenguol AT gmail.com

We are hiring (Chief Scientist/Researcher/Intern):

• Topics: Foundation of Generative AI / AI for Math / AI Agents
• Responsibilities: Conduct frontier AI research on high-impact projects
• Qualifications: Proven track record in AI research and solving real-world problems. Team work.
• Locations: Hong Kong, Shenzhen, Beijing, Nanjing, London

About

I am currently the director of the AI Theory Lab in Huawei Noah’s Ark Lab, and an Adjunct Professor in the department of computer science and engineering, The Hong Kong University of Science and Technology. I was an associate research scientist in the department of electrical engineering, Columbia University, working with Prof. Shih-Fu Chang. I received BS and MS degrees in mathematics at Peking University, and PhD degree in machine learning at The Chinese University of Hong Kong, advised by Prof. Xiaoou Tang. My research interests include machine learning and artificial intelligence. I am an Area Chair of NeurIPS 2023 and ICLR 2024, and selected as 2023 AI 2000 Most Influential Scholar between 2013-2022 (by AMiner) and Top 2% Scientists Worldwide 2023 (by Stanford University).

My current research focus is in the foundation of generative AI and its real-world applications to AIGC, mathematical reasoning, and scientific discovery.

Selected Publications ( google scholar / dblp )

• Complexity Matters: Rethinking the Latent Space for Generative Modeling, NeurIPS 2023, Spotlight
  Tianyang Hu, Fei Chen, Haonan Wang, Jiawei Li, Wenjia Wang, Jiacheng Sun, Zhenguo Li.
  
• DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation, NeurIPS 2023
  Shentong Mo, Enze Xie, Ruihang Chu, Lanqing HONG, Matthias Nießner, Zhenguo Li.
  
• DiffComplete: Diffusion-based Generative 3D Shape Completion, NeurIPS 2023
  Ruihang Chu, Enze Xie, Shentong Mo, Zhenguo Li, Matthias Nießner, Chi-Wing Fu, Jiaya Jia.
  
• Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models, NeurIPS 2023
  Weijian Luo, Tianyang Hu, Shifeng Zhang, Jiacheng Sun, Zhenguo Li, Zhihua Zhang.
  
• SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models, NeurIPS 2023
  Shuchen Xue, Mingyang Yi, Weijian Luo, Shifeng Zhang, Jiacheng Sun, Zhenguo Li, Zhi-Ming Ma.
  
• T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-toimage Generation, NeurIPS 2023, Datasets and Benchmarks Track
  Kaiyi Huang, Kaiyue Sun, Enze Xie, Zhenguo Li, Xihui Liu.
  
• DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning, ICCV 2023, Oral
  Enze Xie, Lewei Yao, Han Shi, Zhili Liu, Daquan Zhou, Zhaoqiang Liu, Jiawei Li, Zhenguo Li.
  
• Beyond One-to-One: Rethinking the Referring Image Segmentation, ICCV 2023, Oral
  Yutao Hu, Qixiong Wang, Wenqi Shao, Enze Xie, Zhenguo Li, Jungong Han, Ping Luo.
  
• DDP: Diffusion Model for Dense Visual Prediction, ICCV 2023
  Yuanfeng Ji, Zhe Chen, Enze Xie, Lanqing Hong, Xihui Liu, Zhaoqiang Liu, Tong Lu, Zhenguo Li, Ping Luo.
  
• MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation, ICCV 2023
  Chongjian Ge, Junsong Chen, Enze Xie, Zhongdao Wang, Lanqing Hong, Huchuan Lu, Zhenguo Li, Ping Luo.
  
• UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation, ICCV 2023
  Haiyang Wang, Hao Tang, Shaoshuai Shi, Aoxue Li, Zhenguo Li, Bernt Schiele, Liwei Wang.
  
• DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function, ACL 2023
  Wang Haiming, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, lin li, Jian Yin, Zhenguo Li, Xiaodan Liang.
  
• Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization, ICML 2023
  Yimeng Chen, Tianyang Hu, Fengwei Zhou, Zhenguo Li, Zhi-Ming Ma.
  
• ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning, CVPR 2023
  Hao Yang, Lanqing Hong, Aoxue Li, Tianyang Hu, Zhenguo Li, Gim Hee Lee, Liwei Wang.
  
• DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment, CVPR 2023
  Lewei Yao, Jianhua Han, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, Hang Xu
  
• Mixed Autoencoder for Self-supervised Visual Representation Learning, CVPR 2023
  Kai Chen, Zhili Liu, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung.
  
• Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts, ICLR 2023, Spotlight, notable-top-25%
  Zhili Liu, Kai Chen, Jianhua Han, Lanqing Hong, Hang Xu, Zhenguo Li, James Kwok.
  
• Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning, ICLR 2023, Spotlight, notable-top-25%
  Jiahui Gao, Renjie Pi, Yong Lin, Hang Xu, Jiacheng Ye, Zhiyong Wu, Weizhong Zhang, Xiaodan Liang, Zhenguo Li, Lingpeng Kong.
  
• Breaking Correlation Shift via Conditional Invariant Regularizer, ICLR 2023
  Mingyang Yi, Ruoyu Wang, Jiacheng Sun, Zhenguo Li, Zhi-Ming Ma.
  
• CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving, ICLR 2023
  Runjian Chen, Yao Mu, Runsen Xu, Wenqi Shao, Chenhan Jiang, Hang Xu, Yu Qiao, Zhenguo Li, Ping Luo.
  
• Fair-CDA: Continuous and Directional Augmentation for Group Fairness, AAAI 2023
  Rui Sun, Fengwei Zhou, Zhenhua Dong, Chuanlong Xie, Lanqing Hong, Jiawei Li, Rui Zhang, Zhen Li, Zhenguo Li
  
• DAMix: Exploiting Deep Autoregressive Model Zoo for Improving Lossless Compression Generalization, AAAI 2023
  Qishi Dong, Fengwei Zhou, Ning Kang, Chuanlong Xie, Shifeng Zhang, Jiawei Li, Heng Peng, Zhenguo Li.
  
• ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization, NeurIPS 2022
  Qishi Dong, Muhammad Awais, Fengwei Zhou, Chuanlong Xie, Tianyang Hu, Yongxin Yang, Sung-Ho Bae, Zhenguo Li.
  
• Understanding Square Loss in Training Overparametrized Neural Network Classifiers, NeurIPS 2022, Spotlight
  Tianyang Hu, Jun Wang, Wenjia Wang, Zhenguo Li.
  
• DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection, NeurIPS 2022
  Lewei Yao, Jianhua Han, Youpeng Wen, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, Chunjing Xu, Hang Xu.
  
• CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds, NeurIPS 2022
  Haiyang Wang, Lihe Ding, Shaocong Dong, Shaoshuai Shi, Aoxue Li, Jianan Li, Zhenguo Li, Liwei Wang.
  
• DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction, ECCV 2022
  Kaichen Zhou, Lanqing Hong, Changhao Chen, Hang Xu, Chaoqiang Ye, Qingyong Hu, Zhenguo Li.
  
• Generative Negative Text Replay for Continual Vision-Language Pretraining, ECCV 2022
  Shipeng Yan, Lanqing Hong, Hang Xu, Jianhua Han,Tinne Tuytelaars, Zhenguo Li, Xuming He.
  
• CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving, ECCV 2022
  Kaican Li, Kai Chen, Haoyu Wang, Lanqing Hong, Chaoqiang Ye, Jianhua Han, Yukuai Chen, Wei Zhang, Chunjing Xu, Dit-Yan Yeung, Xiaodan Liang, Zhenguo Li, Hang Xu.
  
• AutoHash: Learning Higher-order Feature Interactions for Deep CTR Prediction, IEEE Trans. on Knowledge and Data Engineering (TKDE) 2022
  Niannan Xue, Bin Liu, Huifeng Guo, Ruiming Tang, Fengwei Zhou, Stefanos Zafeiriou, Yuzhou Zhang, Jun Wang, Zhenguo Li.
  
• Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors, T-PAMI 2022
  Jian Ding, Enze Xie, Hang Xu, Chenhan Jiang, Zhenguo Li, Ping Luo, Gui-Song Xia.
  
• PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework, CVPR 2022
  Ning Kang, Shanzhao Qiu, Shifeng Zhang, Zhenguo Li, Shu-Tao Xia.
  
• ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation, CVPR 2022, Oral
  Jianan Wang, Guansong Lu, Hang Xu, Zhenguo Li, Chunjing Xu, Yanwei Fu.
  
• OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization, CVPR 2022, Oral
  Nanyang Ye, Kaican Li, Haoyue Bai, Runpeng Yu, Lanqing Hong, Fengwei Zhou, Zhenguo Li, Jun Zhu.
  
• Long-tail Recognition via Compositional Knowledge Transfer, CVPR 2022
  Sarah Parisot, Pedro M Esperanca, Steven McDonagh, Tamas J Madarasz, Yongxin Yang, Zhenguo Li.
  
• Semi-Supervised Object Detection via Multi-instance Alignment with Global Class Prototypes, CVPR 2022
  Aoxue Li, Peng Yuan, Zhenguo Li.
  
• Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search, CVPR 2022
  Minbin Huang, Zhijian Huang, Changlin Li, Xin Chen, Hang Xu, Zhenguo Li, Xiaodan Liang.
  
• Revisiting Over-smoothing in BERT from the Perspective of Graph, ICLR 2022, Spotlight, notable-top-25%
  Han Shi, Jiahui Gao, Hang Xu, Xiaodan Liang, Zhenguo Li, Lingpeng Kong, Stephen M. S. Lee and James Kwok.
  
• On Redundancy and Diversity in Cell-based Neural Architecture Search, ICLR 2022
  Xingchen Wan, Binxin Ru, Pedro M Esperança, Zhenguo Li.
  
• Generalizing Few-Shot NAS with Gradient Matching, ICLR 2022
  Shoukang Hu, Ruochen Wang, Lanqing Hong, Zhenguo Li, Cho-Jui Hsieh and Jiashi Feng.
  
• Rethinking Adversarial Transferability from a Data Distribution Perspective, ICLR 2022
  Yao Zhu, Jiacheng Sun, Zhenguo Li.
  
• Nonlinear ICA Using Volume-Preserving Transformations, ICLR 2022
  Xiaojiang Yang, Yi Wang, Jiacheng Sun, Xing Zhang, Shifeng Zhang, Zhenguo Li, Junchi Yan.
  
• FILIP: Fine-grained Interactive Language-Image Pre-Training, ICLR 2022
  Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, Chunjing Xu.
  
• How Well Does Self-Supervised Pre-Training Perform with Streaming Data?, ICLR 2022
  Dapeng Hu, Shipeng Yan, Qizhengqiu Lu, Lanqing Hong, Hailin Hu, Yifan Zhang, Zhenguo Li, Xinchao Wang and Jiashi Feng.
  
• Memory Replay with Data Compression for Continual Learning, ICLR 2022
  Liyuan Wang, Xingxing Zhang, Kuo Yang, Longhui Yu, Chongxuan Li, Lanqing Hong, Shifeng Zhang, Zhenguo Li, Yi Zhong and Jun Zhu.
  
• Improving Model Training with Multi-fidelity Hyperparameter Evaluation, MLSys 2022
  Yimin Huang, Yujun Li, Hanrong Ye, Zhenguo Li, Zhihua Zhang.
  
• AutoBERT-Zero: Evolving BERT Backbone from Scratch, AAAI 2022
  Jiahui Gao, Hang Xu, Han shi, Xiaozhe Ren, Philip L.H. Yu, Xiaodan Liang, Xin Jiang, Zhenguo Li.
  
• Task-customized Self-supervised Pre-training with Scalable Dynamic Routing, AAAI 2022
  Zhili Liu, Jianhua Han, Lanqing Hong, Hang Xu, Kai Chen, Chunjing Xu, Zhenguo Li.
  
• AIM: Automatic Interaction Machine for Click-Through Rate Prediction, IEEE Trans. on Knowledge and Data Engineering (TKDE) 2022
  Chenxu Zhu, Bo Chen, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, Yong Yu.
  
• iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder, NeurIPS 2021, Spotlight, top 3%
  Shifeng Zhang, Ning Kang, Tom Ryder, Zhenguo Li.
  
• OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression, NeurIPS 2021
  Chen Zhang, Shifeng Zhang, Fabio Maria Carlucci, Zhenguo Li.
  
• On Effective Scheduling of Model-based Reinforcement Learning, NeurIPS 2021
  Hang Lai, Jian Shen, Weinan Zhang, Yimin Huang, Xing Zhang, Ruiming Tang, Yong Yu, Zhenguo Li.
  
• MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps, NeurIPS 2021
  Muhammad Awais, Fengwei Zhou, Chuanlong Xie, Jiawei Li, Sung-Ho Bae, Zhenguo Li.
  
• Towards a Theoretical Framework of Out-of-Distribution Generalization, NeurIPS 2021
  Haotian Ye, Chuanlong Xie, Tianle Cai, Ruichen Li, Zhenguo Li, Liwei Wang.
  
• SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving, NeurIPS 2021, Datasets and Benchmarks Track
  Jianhua Han, Xiwen Liang, Hang Xu, Kai Chen, Lanqing HONG, Chaoqiang Ye, Wei Zhang, Zhenguo Li, Xiaodan Liang, Chunjing Xu.
  
• One Million Scenes for Autonomous Driving: ONCE Dataset, NeurIPS 2021, Datasets and Benchmarks Track
  Jiageng Mao, Minzhe Niu, Chenhan Jiang, hanxue liang, Jingheng Chen, Xiaodan Liang, Yamin Li, Chaoqiang Ye, Wei Zhang, Zhenguo Li, Jie Yu, Chunjing Xu, Hang Xu.
  
• NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models, ICCV 2021
  Hang Xu, Ning Kang, Gengwei Zhang, Chuanlong Xie, Xiaodan Liang, Zhenguo Li.
  
• NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization, ICCV 2021
  Haoyue Bai, Fengwei Zhou, Lanqing Hong, Nanyang Ye, S.-H. Gary Chan, Zhenguo Li.
  
• Exploring Geometry-aware Contrast and Clustering Harmonization for Self-supervised 3D Object Detection, ICCV 2021
  Hanxue Liang, Chenhan Jiang, Dapeng Feng, Xin Chen, Hang Xu, Xiaodan Liang, Wei Zhang, Zhenguo Li, Luc Van Gool.
  
• DetCo: Unsupervised Contrastive Learning for Object Detection, ICCV 2021
  Enze Xie, Jian Ding, Wenhai Wang, Xiaohang Zhan, Hang Xu, Zhenguo Li, Ping Luo.
  
• Multisiam: Self-supervised multi-instance siamese representation learning for autonomous driving, ICCV 2021
  Kai Chen, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung.
  
• G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation, ICCV 2021
  Lewei Yao, Renjie Pi, Hang Xu, Wei Zhang, Zhenguo Li, Tong Zhang.
  
• Adversarial Robustness for Unsupervised Domain Adaptation, ICCV 2021
  Muhammad Awais, Fengwei Zhou, Hang Xu, Lanqing Hong, Ping Luo, Sung-Ho Bae, Zhenguo Li.
  
• Towards Understanding the Generative Capability of Adversarially Robust Classifiers, ICCV 2021, Oral
  Yao Zhu, Jiacheng Ma, Jiacheng Sun, Zewei Chen, Rongxin Jiang, Zhenguo Li.
  
• AutoDis: Automatic Discretization for Embedding Numerical Features in CTR Prediction, KDD 2021
  Huifeng Guo, Bo Chen, Ruiming Tang, Zhenguo Li, Xiuqiang He.
  
• SparseBERT: Rethinking the Importance Analysis in Self-attention, ICML 2021
  Han Shi, Jiahui Gao, Xiaozhe Ren, Hang Xu, Xiaodan Liang, Zhenguo Li, James T. Kwok.
  
• iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression, CVPR 2021
  Shifeng Zhang, Chen Zhang, Ning Kang, Zhenguo Li.
  
• Transformation Invariant Few-Shot Object Detection, CVPR 2021
  Aoxue Li, Zhenguo Li.
  
• Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation, CVPR 2021
  Lewei Yao, Renjie Pi, Hang Xu, Wei Zhang, Zhenguo Li, Tong Zhang.
  
• TransNAS-Bench-101: Improving Transferrability and Generalizability of Cross-Task Neural Architecture Search, CVPR 2021
  Yawen Duan, Xin Chen, Hang Xu, Zewei Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li.
  
• ModularNAS: Towards Modularized and Reusable Neural Architecture Search, MLSys 2021
  Yunfeng Lin, Guilin Li, Xing Zhang, Weinan Zhang, Bo Chen, Ruiming Tang, Zhenguo Li, Jiashi Feng, Yong Yu.
  
• Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search, ICLR 2021
  Peidong Liu, Gengwei Zhang, Bochao Wang, Hang Xu, Xiaodan Liang, Yong Jiang, Zhenguo Li.
  
• Locally Differentially Private (Contextual) Bandits Learning, NeurIPS 2020
  Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li, Liwei Wang.
  
• Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS, NeurIPS 2020
  Han Shi, Renjie Pi, Hang Xu, Zhenguo Li, James T. Kwok, Tong Zhang.
  
• CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending, ECCV 2020
  Hang Xu, Shaoju Wang, Xinyue Cai, Wei Zhang, Xiaodan Liang, Zhenguo Li.
  
• AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction, KDD 2020
  Bin Liu, Chenxu Zhu, Guilin Li, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, Yong Yu.
  
• Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification, ICCV 2019
  Hang Xu, Lewei Yao, Xiaodan Liang, Wei Zhang, Zhenguo Li.
  
• Federated Meta-Learning with Fast Convergence and Efficient Communication, arXiv 22 Feb 2018
  Fei Chen, Mi Luo, Zhenhua Dong, Zhenguo Li, Xiuqiang He.
  
• Deep Meta-Learning: Learning to Learn in the Concept Space, arXiv 10 Feb 2018.
  Fengwei Zhou, Bin Wu, Zhenguo Li.
  
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning, arXiv 31 Jul 2017.
  Zhenguo Li, Fengwei Zhou, Fei Chen, Hang Li.
  
• Graph Edge Partitioning via Neighborhood Heuristic, KDD 2017, oral.
  Chenzi Zhang, Fan Wei, Qin Liu, Zhihao Tang, Zhenguo Li.
  
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction, IJCAI 2017.
  Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, Xiuqiang He.
  
• VENUS: A System for Streamlined Graph Computation on a Single PC, IEEE Trans. on Knowledge and Data Engineering (TKDE), 2016.
  Qin Liu, Jiefeng Cheng, Zhenguo Li, John C.S. Lui.
  
• Walking in the Cloud: Parallel SimRank at Scale, PVLDB 2016.
  Zhenguo Li, Yixiang Fang, Qin Liu, Jiefeng Cheng, Reynold Cheng, and John C.S. Lui.
• VENUS: Vertex-Centric Streamlined Graph Computation on a Single PC, ICDE 2015.
  Jiefeng Cheng, Qin Liu, Zhenguo Li, Wei Fan, John C.S. Lui, and Cheng He.
• Locally Linear Hashing for Extracting Non-Linear Manifolds, CVPR 2014.
  Go Irie, Zhenguo Li, Xiao-Ming Wu, and Shih-Fu Chang.
• Analyzing the Harmonic Structure in Graph-Based Learning, NIPS 2013.
  Xiao-Ming Wu, Zhenguo Li, and Shih-Fu Chang.
• Learning with Partially Absorbing Random Walks, NIPS 2012.
  Xiao-Ming Wu, Zhenguo Li, Anthony Man-Cho So, John Wright, and Shih-Fu Chang.
• Segmentation Using Superpixels: A Bipartite Graph Partitioning Approach, CVPR 2012.
  Zhenguo Li, Xiao-Ming Wu, and Shih-Fu Chang.
• Fast Graph Laplacian Regularized Kernel Learning via Semidefinite-Quadratic-Linear Programming, NIPS 2009.
  Xiao-Ming Wu, Anthony Man-Cho So, Zhenguo Li, and Shuo-Yen Robert Li.
• Constrained Clustering via Spectral Regularization, CVPR 2009.
  Zhenguo Li, Jianzhuang Liu, and Xiaoou Tang.
• Pairwise Constraint Propagation by Semidefinite Programming for Semi-Supervised Classification, ICML 2008.
  Zhenguo Li, Jianzhuang Liu, and Xiaoou Tang.
• Plane-Based Optimization for 3D Object Reconstruction from Single Line Drawings, T-PAMI, 2008.
  Jianzhuang Liu, Liangliang Cao, Zhenguo Li, and Xiaoou Tang.