王威，北京科技大学，计算机与通讯工程学院，特聘教授。2005年获武汉大学自动化专业学士学位，2011年获中国科学院大学计算机应用技术专业博士学位。2011年进入中国科学院自动化研究所模式识别国家重点实验室工作，2015年晋升为副研究员。2021年加入北京通用人工智能研究院，任认知与推理实验室主任、研究员，2026年全职加入北京科技大学。

开展认知推理与计算建模、计算机视觉、具身智能、AI for Science研究，发表国际期刊和国际会议论文80多篇，包括Nature Machine Intelligence、TPAMI、TIP、ICLR、NIPS、ICCV、CVPR、AAAI等，Google总引用10800多次，两篇文章引用过千次（CVPR 2015 单篇他引 2800 多次，CVPR 2019 单篇他引 1100 多次），相关研究工作获得最佳论文奖（CVPR DeepVision Workshop 2014）、ICPR2014最佳学生论文奖。研究成果授权专利15项，领导开发了基于TongSIM的通用人工智能示教学习平台TongCloud，参与开发了用于训练与评估具身智能体的高保真通用平台TongSIM。主持3项国家自然科学基金项目（2个面上1个青基），主持多项企业合作项目（国家电网、腾讯）。指导10多名博、硕士研究生开展研究工作，1名学生获得中科院优秀博士学位论文。

招生：每年招收1名博士、2名硕士，1～2名博士后，希望与有意在人工智能理论与应用方面作出有影响力工作的同学、老师合作。

课程教学

· 《推理中的直觉与逻辑》，2025年清华24级科研实践课，2025.6.30

· 《深度学习》，中国科学院大学，研究生课程（全日），40课时，2017/2018/2019春季学期

· 《深度学习》，中国科学院大学，研究生课程（非全），40课时，2017/2018/2019春季学期

· 《模式识别研讨与实践》，中国科学院大学，研究生课程（全日），20课时，2017春季学期

代表性论著（Google Scholar）

[1] Chi Zhang, Jiajun Song, Siyu Li, Yitao Liang, Yuxi Ma, Wei Wang, Yixin Zhu, Song-Chun Zhu.Proposing and solving olympiad geometry with guided tree search. Nature Machine Intelligence, 2026.（共同通讯,封面文章）

[2] Yi-Long Lu, Jiajun Song, Wei Wang. A Unified Representation Underlying the Judgment of Large Language Models. arXiv:2510.27328, under revision， Nature Communications. （共同通讯）

[3] Boyuan Zhang, Yuxuan Wang, Yizhou Wang, Wei Wang and Zhenliang Zhang. Active Kinematic Modeling for Precise Manipulation of Unseen Articulated Objects. Robotics and Automation Letters (RAL), 2026（共同通讯）

[4] Yi-Long Lu, Jiajun Song, Chunhui Zhang, Wei Wang. Mind the Gap: The Divergence Between Human and LLM-Generated Tasks. AAAI, 2026（通讯）

[5] Yi-Long Lu, Chunhui Zhang, Wei Wang. Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks. CogSci, 2025.（通讯）

[6] Yuxuan Wang, Mingzhou Liu, Xinwei Sun, Wei Wang, Yizhou Wang. Bayesian Intervention Optimization for Causal Discovery. ICML, 2025.（共同通讯）

[7] Wei, Chenrui, Mengzhou Sun, Wei Wang. Proving Olympiad Algebraic Inequalities without Human Demonstrations. NeurIPS, 2024.（通讯）

[8] Wu, Rujie, Xiaojian Ma, Qing Li, Wei Wang, Zhenliang Zhang, Song-Chun Zhu, and Yizhou Wang. Bongard-OpenWorld: Few-shot reasoning for free-form visual concepts in the real world. ICLR, 2024.（共同通讯）

[9] Qian, Yilue, Peiyu Yu, Ying Nian Wu, Wei Wang, and Lifeng Fan. Learning Concept-Based Visual Causal Transition and Symbolic Reasoning for Visual Planning. IROS, 2024.（共同通讯）

[10] Zhenliang Zhang, Zeyu Zhang, Ziyuan Jiao, Yao Su, Hangxin Liu, Wei Wang, Song-Chun Zhu. On The Emergence of Symmetrical Reality. IEEE Conference Virtual Reality and 3D User Interfaces (VR), 2024.

[11] Wentao Chen, Zhang Zhang, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan. Few-shot learning with unsupervised part discovery and part-aligned similarity. PR. 2023.
[12] Mengmeng Cui, Wei Wang, Kunbo Zhang, Zhenan Sun, Liang Wang. Pose-Appearance Relational Modeling for Video Action Recognition. TIP, 2022.（通讯）

[13] Wentao Chen, Zhang Zhang, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan. Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations. ECCV, 2022.

[14] Wentao Chen, Chenyang Si, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan. Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images. IJCAI, 2021.

[15] Ya Jing, Tao Kong, Wei Wang, Liang Wang, Lei Li, Tieniu Tan. Locate then Segment: A Strong Pipeline for Referring Image Segmentation. CVPR, 2021.

[16] Ya Jing, Wei Wang, Liang Wang, Tieniu Tan. Learning Aligned Image-Text Representations Using Graph Attentive Relational Network. TIP, 2021.（通讯） 

[17] Chenyang Si, Ya Jing, Wei Wang, Liang Wang, Tieniu Tan. Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network. PR, 2020.（通讯）

[18] Ya Jing, Junbo Wang, Wei Wang, Liang Wang, Tieniu Tan. Relational graph neural network for situation recognition. PR, 2020.（通讯）

[19] Chenyang Si, Xuecheng Nie, Wei Wang, Liang Wang, Tieniu Tan, Jiashi Feng. Adversarial Self-supervised Learning for Semi-supervised 3D Action Recognition. ECCV, 2020.

[20] Ya Jing, Wei Wang, Liang Wang, Tieniu Tan. Cross-Modal Cross-Domain Moment Alignment Network for Person Search. IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2020.（通讯）

[21] Ya Jing, Chenyang Si, Wei Wang, Liang Wang, Tieniu Tan. Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search. AAAI Conference on Artificial Intelligence, AAAI, 2020 (oral).（通讯）

[22] Jingyu Liu, Wei Wang, Liang Wang, Ming-Hsuan Yang. Attribute-Guided Attention for Referring Expression Generation and Comprehension, TIP, 2020.

[23] Junbo Wang, Wei Wang, Liang Wang, Zhiyong Wang, David Dagan Feng, Tieniu Tan. Learning visual relationship and context-aware attention for image captioning, PR, 2020.（通讯）

[24] Chenyang Si, Wentao Chen, Wei Wang, Liang Wang, Tieniu Tan. An Attention Enhanced Graph Convolutional Lstm Network for Skeleton-based Action Recognition. CVPR, 2019.（通讯）

[25] Kun Yu, Zhiyong Wang, Wei Wang, K. Martens, Liang Wang, Tieniu Tan, S. Lewis, D. Feng. Graph Sequence Recurrent Neural Network for Vision-Based Freezing of Gait Detection, TIP, 2019.

[26] Junbo Wang, Wei Wang, Zhiyong Wang, Liang Wang, David Feng, Tieniu Tan. Stacked Memory Network for Video Summarization. ACM Multimedia. ACM MM, 2019.（通讯）

[27] Chenyang Si, Wei Wang, Liang Wang, Tieniu Tan. Multistage Adversarial Losses for Pose-based Human Image Synthesis. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, 2018 (spotlight).（通讯）

[28] Chenyang Si, Ya Jing, Wei Wang, Liang Wang, Tieniu Tan. Skeleton-based action recognition with spatial reasoning and temporal stack learning. European Conference on Computer Vision. ECCV, 2018.（通讯）

[29] Junbo Wang, Wei Wang, Yan Huang, Liang Wang, Tieniu Tan. Multimodal Memory Modelling for Video Captioning. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, 2018 (spotlight).（通讯）

[30] Junbo Wang, Wei Wang, Yan Huang, Liang Wang, Tieniu Tan. Hierarchical Memory Modelling for Video Captioning. ACM Multimedia. ACM MM, 2018.（通讯）

[31] Yan Huang, Wei Wang, Liang Wang. Instance-Aware Image and Sentence Matching With Selective Multimodal LSTM. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, 2017.

[32] Yan Huang, Wei Wang, Liang Wang. Video Super-Resolution via Bidirectional Recurrent Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. TPAMI, 2017.

[33] Yan Huang, Wei Wang, Liang Wang. Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution. Advances in Neural Information Processing Systems. NIPS, 2015. 

[34] Yan Huang, Wei Wang, Liang Wang. Conditional High-order Boltzmann Machine: A Supervised Learning Model for Relation Learning. IEEE International Conference on Computer Vision. ICCV, 2015.

[35] Yong Du, Wei Wang, Liang Wang. Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, 2015.

[36] Peihao Huang, Yan Huang, Wei Wang, Liang Wang, Tieniu Tan. Deep Embedding Network for Clustering. International Conference on Pattern Recognition. ICPR, 2014 (best student paper).

[37] Wei Wang, Yan Huang, Yizhou Wang, Liang Wang. Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction. IEEE Conference on Computer Vision and Pattern Recognition CVPR Workshop: DeepVision - Deep Learning for Computer Vision. CVPRW, 2014 (oral, best paper).

[38] Wei Wang, Cheng Chen, Yizhou Wang, Tingting Jiang, Fang Fang, Yuan Yao. Simulating Human Saccadic Scanpath on Natural Images. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, 2011.

[39] Wei Wang, Yizhou Wang, Qingming Huang, Wen Gao. Measuring Visual Saliency by Site Entropy Rate. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, 2010 (oral).