Yang Wenming

2003.9-2006.7   Ph.D., Information Science & Electronic Engineering (ISEE), Zhejiang University 

1996.9-2003.9   Bachelor's & Master's, Harbin University of Science and Technology 

2025.12- present   Professor, Institute of Data & Information of Tsinghua SIGS  

2017.06-2017.09   Academic Visitor,  Department of Statistical Sciences of University College London  

2013.12-2025.12  Associate Professor,  Division of Information Sciences/ Institute of Data & Information of Tsinghua SIGS  

2010.1-2013.12     Assistant Professor,  Division of Information Sciences of Tsinghua SIGS  

2008.1-2009.12     PostDoc., Tsinghua University

2006.7-2007.12     Assistant Professor,  China Jiliang University

IEEE Senior Member，CAAI、CSIG、CCF Member

《Digital Image Processing & Its Applications》

《Practices of Digital Image Processing》

《Biomedical & Information Experiments》

As a supervisor, he has guided:

·11 Tsinghua University Outstanding Master’s Theses (Top 5%)

·10 Tsinghua University or Beijing Municipal Outstanding Master’s Graduates

·2 National Outstanding Engineering Master’s Internship Achievement Awardees (approximately 100 selected nationwide annually)

·2 PhD National Scholarship recipients

·6 Master’s National Scholarship recipients

·1 Tsinghua Shenzhen International Graduate School (TSIGS) Academic Rising Star (Top 0.1%)

·1 TSIGS Academic Rising Star Nomination

·2 TSIGS Professional Practice First Prize winners (ranking 1st institute-wide, Top 0.1%)

·1 Tsinghua University Outstanding Doctoral Dissertation(co-supervisor)

Recruitment Information:

He admits approximately 6–8 Master’s and PhD students each year. He strongly encourages academic innovation, technology translation, and international exchange or further study. Prospective students with strong foundations in mathematics and English are especially welcome to apply.

Long-term Openings for Postdoctoral Researchers in the following areas: Computer Vision, Deep Learning, Medical Artificial Intelligence, and AI Large Models.

Computer Vision, Deep Learning, Artificial Intelligence and Multimodal Large Models.

As project leader or core member, Professor Yang has finished more than 10 scientific research projects including of National key research & development program, National Natural Science Foundation of China, Natural Science Foundation Guangdong Province, Key Natural Science Foundation of Shenzhen, and more than 20 technology development projects including of HUAWEI and DJI companies.

His research primarily focuses on the fields of image processing, computer vision, deep learning, and artificial intelligence. Specific areas include visual enhancement and restoration, visual object perception, visual 3D reconstruction, medical AI, deep learning, reinforcement learning, and multimodal large models (covering foundation models, hallucination, chain-of-thought, AIGC evaluation, and vertical applications). As the Responsible Professor, he spearheaded the creation of the nation’s first full-time Master’s program in Large Model Science and Engineering. As the principal investigator, he has led dozens of research projects, including sub-projects of the National Key R&D Program, the National Natural Science Foundation of China (Young Scientists Fund, General Program), the Royal Society International Collaboration and Exchange Fund (UK), the Postdoctoral Science Foundation, the Guangdong Provincial Natural Science Foundation, the Shenzhen Basic Research General Program and Key Program, the Shenzhen Key Technology R&D Program, internal university funds for young researchers, interdisciplinary research funds, international collaboration funds, as well as commissioned R&D and collaborative projects with leading industry partners such as Huawei, DJI, and State Grid.

In recent years, he has published nearly 200 papers in prestigious international journals, including Nature Communications, IEEE TPAMI, TSPM, TIP, TNNLS, TCSVT, TMM, TSMC, JBHI, and Pattern Recognition, as well as at top-tier international conferences such as IEEE/CVF ICCV, CVPR, AAAI, ICML, ICLR, ACM Multimedia, ICASSP, and MICCAI. His Google Scholar citation count exceeds 7,500, with 2 ESI Highly Cited Papers and 1 ESI Hot Paper. He has also served as a guest editor, co-organizing two special issues for the renowned international journals Neurocomputing and Signal Processing: Image Communication.

Additionally, he has applied for more than 20 invention patents, several of which have been successfully commercialized, generating significant economic benefits.

Special Issue on Neurocomputing 

Topic：Deep Learning for Image Super-Resolution

Special Issue on Signal Processing：Image Communication

Topic：Advances in statistical methods based VQA

[1] Zhehan Kan, Xin Li, Yanlin Liu, Xiaochen Yang, Xinghua Jiang, Yinsong Liu, Deqiang Jiang, Xing Sun, Qingmin Liao, Wenming Yang*，RAR: Reversing Visual Attention Re-Sinking for Unlocking Potential in Multimodal Large Language Models，ICLR 2026(Accepted)

[2] Junyang Ji, Shengjun Zhang, Da Li, Yuxiao Luo, Yan Wang, Di Xu, Biao Yang, Wei Yuan, Fan Yang, Zhihai He*, Wenming Yang*, OmniCVR: A Benchmark for Omni-Composed Video Retrieval with Vision, Audio, and Text, ICLR 2026(Accepted)

[3] Fan Zhang, Sinchee Chin, Jing-Hao Xue, Wenming Yang*, ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly Detection, ICLR 2026(Accepted)

[4] Zhun Mou, Bin Xia, Zhengchao Huang, Wenming Yang*, Jiaya Jia, GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning, ICML 2025

[5] Yuheng Yang, Yudong Lin, Wenming Yang*, Guijin Wang, Qingmin Liao, SAP-SLAM: Semantic-Assisted Perception SLAM with 3D Gaussian Splatting, ICRA 2025: 8493-8499

[6] Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xinglong Wu, Yapeng Tian, Wenming Yang*, Radu Timofte, Luc Van Gool: DiffI2I: Efficient Diffusion Model for Image-to-Image Translation, IEEE Trans. on Pattern Analysis and Machine Intelligence(IEEE TPAMI), 47(3):1578-1593 (2025).

[7] Yuan Shi, Bin Xia, Xiaoyu Jin, Xing Wang, Tianyu Zhao, Xin Xia, Xuefeng Xiao, Wenming Yang*: VmambaIR: Visual State Space Model for Image Restoration, IEEE Trans. on Circuits Systems & Video Technology(IEEE TCSVT), (2025 Accepted).

[8] Fanqi Pu, Yifan Wang, Jiru Deng, Wenming Yang*: MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors, CVPR 2025(Accepted).

[9] Jiaqi Lin, Zhihao Li, Binxiao Huang, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Xiaofei Xu, Fenglong Song, Wenming Yang*: Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting, AAAI 2025(Accepted).

[10] Xinyi Zhang, Qiqi Bao, Qinpeng Cui, Wenming Yang, Qingmin Liao*: Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network, AAAI 2025(Accepted).

[11] Peng Ling, Tiao Tan, Jiaqi Lin, Wenming Yang*: SOVGaussian: Sparse-View 3D Gaussian Splatting for Open-Vocabulary Scene Understanding, AAAI 2025(Accepted).

[12] Jintong Hu, Bin Xia, Bin Chen, Wenming Yang*, Lei Zhang: GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution, AAAI 2025(Accepted).

[13]  Zongkai Zhang, Bin Gao, Jingrui Ye, Huan Jin, Lihui Jiang, Wenming Yang*: CLIP Prior-Guided 3D Open-Vocabulary Occupancy Prediction, Pattern Recognition(PR). 2025(Accepted).

[14] Fengyi Fang, Zhehan Kan, Wenming Yang: MDSI: Pluggable Multi-Strategy Decoupling with Semantic Integration for RGB-D Gesture Recognition, Pattern Recognition(PR). 2025(Accepted).

[15] Peng Lu, Tao Jiang, Yining Li, Xiangtai Li, Kai Chen, Wenming Yang*: RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation, CVPR 2024.

[16] Jiaqi Lin, Zhihao Li, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Jiayue Liu, Yangdi Lu, Xiaofei Wu, Songcen Xu, Youliang Yan, Wenming Yang*: VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction, CVPR 2024.

[17] Xinyi Zhang, Qinpeng Cui, Qiqi Bao, Wenming Yang, Qingmin Liao*: Geometry-Guided Diffusion Model with Masked Transformer for Robust Multi-View 3D Human Pose Estimation, ACM MM 2024.

[18] Zhilin Huang, Quanmin Liang, Yijie Yu, Chujun Qin, Xiawu Zheng, Kai Huang, Zikun Zhou, Wenming Yang*: Bilateral Event Mining and Complementary for Event Stream Super-Resolution, CVPR 2024.

[19] Zhilin Huang, Ling Yang, Xiangxin Zhou, Zhilong Zhang, Wentao Zhang, Xiawu Zheng, Jie Chen, Yu Wang, Bin Cui, Wenming Yang*: Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models, ICLR 2024.

[20] Qiqi Bao, Zheng Hui, Rui Zhu, Peiran Ren, Xuansong Xie, and Wenming Yang*: Improving Diffusion-Based Image Restoration with Error Contraction and Error Correction, AAAI 2024.

[21] Zhilin Huang, Ling Yang, Zaixi Zhang, Xiangxin Zhou, Yu Bao, Xiawu Zheng, Yuwei Yang, Yu Wang, Wenming Yang*: Binding-Adaptive Diffusion Models for Structure-Based Drug Design, AAAI 2024.

[22] Pengyang Zhao, Yizhuo Song, Siqi Wang, Jing-Hao Xue, Shuping Zhao, Qingmin Liao, Wenming Yang*: VPCFormer: A transformer-based multi-view finger vein recognition model and a new benchmark, Pattern Recognition(PR). 148: 110170 (2024).

[23] Yanjun Liu, Wenming Yang*, Qingmin Liao, DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication, IEEE Trans. on Circuits Systems & Video Technology(IEEE TCSVT). 34(12): 12977-12990 (2024).

[24] Siqi Wang, Yehu Shen, Wenming Yang*, Touchless Finger Vein and Fingerprint Verification via Exploiting Attention-Based Cross-Domain Fusion, IEEE Trans. on Circuits Systems & Video Technology(IEEE TCSVT), (2024) Early Access.

[25] Pengyang Zhao, Shuping Zhao, Jing-Hao Xue, Wenming Yang*, Qingmin Liao: The neglected background cues can facilitate finger vein recognition, Pattern Recognition(PR). 136: 109199 (2023).

[26] Yiyun Chen, Yunmeng Liu, Mingliang Chen, Zirui Wang，Wenming Yang*， Qingmin Liao: Blind JPEG Compression Artifacts Removal by Integrating Channel Regulation with Exit Strategy, IEEE Trans. on Multimedia(IEEE TMM), 25(11):7274-7286 (2023).

[27] Hai Wang, Wenming Yang*, Qingmin Liao, Jie Zhou: Bi-RSTU: Bidirectional Recurrent Upsampling Network for Space-Time Video Super-Resolution, IEEE Trans. on Multimedia(IEEE TMM), 25(6): 4742-4751(2023).

[28] Yizhuo Song, Pengyang Zhao, Wenming Yang*, Qingmin Liao, Jie Zhou: EIFNet: An Explicit and Implicit Feature Fusion Network for Finger Vein Verification, IEEE Trans. on Circuits Systems & Video Technol(IEEE TCSVT), 33(5): 2520-2532 (2023)

[29] Bin Xia, Yapeng Tian, Yulun Zhang, Yucheng Hang, Wenming Yang*, Qingmin Liao :Meta-Learning-Based Degradation Representation for Blind Super-Resolution. IEEE Trans. on Image Processing(IEEE TIP), 32: 3383-3396 (2023)

[30] Yi Chen, Yang Dong, Lu Si, Wenming Yang* , Shan Du, Xuewu Tian, Chao Li, Qingmin Liao, Hui Ma: Dual Polarization Modality Fusion Network for Assisting Pathological Diagnosis. IEEE Trans. on Medical Imaging(IEEE TMI), 42(1): 304-316 (2023)

[31] Bin Xia, Jingwen He, Yulun Zhang, Yitong Wang, Yapeng Tian, Wenming Yang*, Luc Van Gool: Structured Sparsity Learning for Efficient Video Super-Resolution, CVPR 2023.

[32] Bin Xia, Yulun Zhang, Yitong Wang, Yapeng Tian, Wenming Yang*, Radu Timofte, Luc Van Gool: Basic Binary Convolution Unit for Binarized Image Restoration Network, ICLR 2023.

[33] Bin Xia, Yulun Zhang, Yitong Wang, Yapeng Tian, Wenming Yang*, Radu Timofte, Luc Van Gool: Knowledge Distillation based Degradation Estimation for Blind Super-Resolution, ICLR 2023.

[34] Ruofan Zhang, Jinjin Gu, Haoyu Chen, Chao Dong, Yulun Zhang, Wenming Yang*: Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution, ICML 2023.

[35] Yingfan Tao, Jingna Sun, Hao Yang, Li Chen, Wenming Yang*, Daniel Du, Min Zheng, Local and Global Logit Adjustments for Long-Tailed Learning, ICCV 2023.

[36] Bin Xia, Yulun Zhang , Shiyin Wang, Yitong Wang, Xinglong Wu, Yapeng Tian, Wenming Yang*, Luc Van Gool: DiffIR: Efficient Diffusion Model for Image Restoration, ICCV 2023.

[37] Yue Lv, Jinxi Xiang, Jun Zhang, Wenming Yang*, Xiao Han, Wei Yang: Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression, ACM MM 2023.

[38] Xiuzhe Wu, Pengfei Hu, Yang Wu, Xiaoyang Lyu, Yan-Pei Cao, Ying Shan, Wenming Yang, Zhongqian Sun, Xiaojuan Qi: Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video, ICCV 2023.

[39] Qiqi Bao; Yunmeng Liu; Bowen Gang; Wenming Yang*; Qingmin Liao, SCTANet: A Spatial Attention-Guided CNN-Transformer Aggregation Network for Deep Face Image Super-Resolution, IEEE Trans. on Multimedia(IEEE TMM), 25(1): 8554-8565(2023).

[40] Yizhuo Song; Pengyang Zhao; Siqi Wang; Qingmin Liao; Wenming Yang*. Study of 3D Finger Vein Biometrics on Imaging Device Design and Multi-View Verification. IEEE Trans. Circuits Systems & Video Technology(IEEE TCSVT), 34(4): 3043-3048(2023).

[41] Wenhao Li, Hong Liu*, Runwei Ding, Mengyuan Liu, Pichao Wang, Wenming Yang: Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation, IEEE Trans. on Multimedia(IEEE TMM), 25(1): 1282-1293 (2023).

[42] Qiqi Bao , Yunmeng Liu , Bowen Gang , Wenming Yang*, Qingmin Liao:S2Net: Shadow Mask-Based Semantic-Aware Network for Single-Image Shadow Removal, IEEE Trans. on Consumer Electronics(IEEE TCE), 68(3): 209-220 (2022)

[43] Pengyang Zhao , Shuping Zhao , Luyang Chen, Wenming Yang* , Qingmin Liao:Exploiting Multiperspective Driven Hierarchical Content-Aware Network for Finger Vein Verification. IEEE Trans. Circuits Systems & Video Technology(IEEE TCSVT), 32(11): 7938-7950 (2022).

[44] Yingfan Tao , Wenxian Zheng, Wenming Yang* , Guijin Wang , Qingmin Liao: Frontal-Centers Guided Face: Boosting Face Recognition by Learning Pose-Invariant Features, IEEE Trans. on Information & Forensics Security(IEEE TIFS), 17(6): 2272-2283 (2022).

[45] Qiqi Bao , Bowen Gang , Wenming Yang* , Jie Zhou , Qingmin Liao: Attention-Driven Graph Neural Network for Deep Face Super-Resolution. IEEE Trans. on Image Processing(IEEE TIP), 31(10): 6455-6470 (2022).

[46] Liyang Liu , Bochao Wang, Zhanghui Kuang, Jing-Hao Xue , Yimin Chen, Wenming Yang* , Qingmin Liao , Wayne Zhang :GenDet: Meta Learning to Generate Detectors From Few Shots. IEEE Trans. on Neural Networks &Learning Systems(IEEE TNNLS), 33(8): 3448-3460 (2022).

[47] Bin Xia, Yucheng Hang, Yapeng Tian, Wenming Yang*, Qingmin Liao, Jie Zhou: Efficient Non-local Contrastive Attention for Image Super-resolution, AAAI 2022.

[48] Bin Xia, Yapeng Tian, Yucheng Hang, Wenming Yang*, Qingmin Liao, Jie Zhou: Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-resolution, AAAI 2022.

[49] Zhenduo Zhang, Yongru Chen, Wenming Yang*, Guijin Wang, Qingmin Liao: Pose-Invariant Face Recognition via Adaptive Angular Distillation, AAAI 2022.

[50] Yucheng Hang, Bin Xia, Wenming Yang*, Qingmin Liao: SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization, CVPR 2022.

[51] Qiqi Bao, Rui Zhu, Bowen Gang, Pengyang Zhao, Wenming Yang*, Qingmin Liao:Distilling Resolution-robust Identity Knowledge for Texture-Enhanced Face Hallucination, ACM Multimedia 2022.

[52] Hai Wang, Xiaoyu Xiang, Yapeng Tian, Wenming Yang*, Qingmin Liao: STDAN: Deformable Attention Network for Space-Time Video Super-Resolution, IEEE Trans. on Multimedia(IEEE TMM), 25(2):1-11 (2023)

[53] Liyang Liu , Zhanghui Kuang, Yimin Chen, Jing-Hao Xue , Wenming Yang* , Wayne Zhang : IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection, IEEE Trans. on Neural Networks & Learning Systems(IEEE TNNLS), 32(6): 2306-2319 (2021)

[54] Wanping Zhang , Yongru Chen , Wenming Yang* , Guijin Wang , Jing-Hao Xue , Qingmin Liao: Class-Variant Margin Normalized Softmax Loss for Deep Face Recognition, IEEE Trans. on Neural Networks & Learning Systems(IEEE TNNLS), 32(10): 4742-4747 (2021)

[55] Wenming Yang, Changqing Hui , Daren Sun, Xiang Sun, Qingmin Liao: Clustering Through Probability Distribution Analysis Along Eigenpaths, IEEE Trans. on Systems, Man, and Cybernatics: Systems(IEEE TSMC-S), 51(2): 875-884 (2021).

[56] Liyang Liu, Yi Li, Zhanghui Kuang, Jing-Hao Xue, Yimin Chen, Wenming Yang*, Qingmin Liao, Wayne Zhang: Towards Impartial Multi-task Learning, ICLR 2021.

[57] Liyang Liu, Shilong Zhang, Zhanghui Kuang, Aojun Zhou, Jing-Hao Xue, Xinjiang Wang, Yimin Chen, Wenming Yang*, Qingmin Liao, Wayne Zhang: Group Fisher Pruning for Practical Network Compression, ICML 2021.

[58] Peng Lu, Gao Huang, Hangyu Lin, Wenming Yang*, Guodong Guo, Yanwei Fu: Domain-Aware SE Network for Sketch-based Image Retrieval with Multiplicative Euclidean Margin Softmax, ACM Multimedia 2021.

[59] Wenming Yang*, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue, Qingmin Liao: LCSCNet: Linear Compressing-Based Skip-Connecting Network for Image Super-Resolution, IEEE Trans. Image Processing(IEEE TIP), 29(9): 1450-1464 (2020).

[60] Jingna Sun , Wenming Yang* , Jing-Hao Xue , Qingmin Liao: An Equalized Margin Loss for Face Recognition. IEEE Trans. on Multimedia(IEEE TMM), 22(11): 2833-2843 (2020).

[61] Yucheng Hang, Qingmin Liao, Wenming Yang*, Yupeng Chen, Jie Zhou: Attention Cube Network for Image Restoration, ACM Multimedia 2020.

[62] Wenming Yang, Zhiquan Chen , Chuan Qin, Qingmin Liao: Alpha-Trimmed Weber Representation and Cross Section Asymmetrical Coding for Human Identification Using Finger Images, IEEE Trans. on Information & Forensics Security(IEEE TIFS), 14(1): 90-101 (2019).

[63] Wenming Yang* , Changqing Hui , Zhiquan Chen , Jing-Hao Xue , Qingmin Liao: FV-GAN: Finger Vein Representation Using Generative Adversarial Networks, IEEE Trans. on Information & Forensics Security(IEEE TIFS), 14(9): 2512-2524 (2019).

[64] Wenming Yang* , Xuechen Zhang , Yapeng Tian, Wei Wang , Jing-Hao Xue , Qingmin Liao: Deep Learning for Single Image Super-Resolution: A Brief Review. IEEE Trans. on Multimedia(IEEE TMM), 21(12): 3106-3121 (2019).

[65] Wei Wang, Ruiming Guo , Yapeng Tian, Wenming Yang*: CFSNet: Toward a Controllable Feature Space for Image Restoration, ICCV 2019.

·Repeatedly listed among the world's Top 2% most-cited scientists (released by Stanford University)

·First Prize of Tsinghua University Teaching Achievement Award (2025)

·Tsinghua University 19th Distinguished Mentor & Friend Award (2024)

·Wu Wenjun Artificial Intelligence Scientific and Technological Progress First Prize (2023)

·First Prize, National Artificial Intelligence Application Scenario Innovation Challenge (2023)

·Shenzhen Artificial Intelligence Natural Science First Prize (2021)

·Selected as Shenzhen High-Level Professional Talent – Local Leading Talent (2016)

·China Society of Surveying and Mapping Geographic Information Science and Technology Progress Award (2016)

·Best Youth Scientific and Technological Achievement Award, National Youth Forum of Chinese Association for Artificial Intelligence (2013)

·Repeatedly recognized as Annual Outstanding Individual of Tsinghua Shenzhen International Graduate School

·Repeatedly honored with Tsinghua University Outstanding Graduate Student Supervisor Award