基本信息

张煦尧 研究员 博士生导师
中国科学院自动化研究所
多模态人工智能系统全国重点实验室

国家优秀青年科学基金获得者
科技创新2030重大项目青年科学家
中科院稳定支持基础研究青年团队
吴文俊人工智能优秀青年奖
中科院朱李月华优秀教师奖
中科院自动化所特聘青年骨干

电子邮件： xyz@nlpr.ia.ac.cn
通信地址： 北京市中关村东路95号
邮政编码： 100190

研究领域

模式识别、机器学习、深度学习、计算机视觉、多模态大模型、AI4Science

招生信息

依托中国科学院自动化研究所、国科大人工智能学院、国科大前沿交叉科学学院、北京中关村学院，每年招收直博生、普通博士生和硕士生。课题组迫切需要有学术追求并对科研充满热情的学生加入，欢迎提前邮件联系。

招生要求：专业背景不限，希望有扎实的数理基础、较好的英语读写能力和编程能力，专注于科研的精神和追求高水平学术的理想。倡导开放的学术氛围，鼓励自由探索，寻找有潜力和热情的同学，支持每位同学快速成长，站在国际学术最前沿。

近年来，实验室学生在人工智能领域顶会（如CVPR, ICCV, NeurIPS, ICLR, ACL, AAAI, IJCAI等）和顶刊（如IEEE TPAMI, TIP, TNNLS, IJCV等）上均有高水平论文发表。课题组学生去向包括BAT华为等大厂，创业公司，科研院校，以及海外博士生或博士后深造。

教育与工作经历

教育经历

2008-2013：中科院自动化所，模式识别与智能系统，博士 （导师：刘成林研究员），CCF优博

2004-2008：武汉大学，计算数学，学士，湖北省优秀学士论文

工作经历

2013至今：中国科学院自动化研究所，助理研究员，副研究员，研究员

2020至今：中国科学院大学，人工智能学院，岗位教授

2015：蒙特利尔大学，国家公派访问学者，Prof. Yoshua Bengio

2012：加拿大模式识别与机器智能中心，访问学者，Prof. Ching Y. Suen

学术服务

Senior Area Editor (SAE), IEEE Trans. Image Processing

Associate Editor (AE), Pattern Recognition

Associate Editor (AE), Neural Networks

Associate Editor (AE), Neurocomputing

Publication Chair, Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2025)

Publication Chair, International Conference on Document Analysis and Recognition (ICDAR 2025)

Publication Chair, Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2024)

Publication Chair, IAPR Asian Conference on Pattern Recognition (ACPR 2017)

Publication Chair, International Conference on Frontiers in Handwriting Recognition (ICFHR 2016)

中国自动化学会，模式识别与机器智能专委会，副秘书长

中国人工智能学会，青年工作委员会，委员

中国图象图形学学会，文档图像分析与识别专委会，委员

教学情况

2025秋季，本科生课程，《模式识别研讨课》，中国科学院大学（雁栖湖）

2025秋季，研究生课程，《模式识别原理与方法》，中国科学院大学（玉泉路）

2024秋季，本科生课程，《模式识别研讨课》，中国科学院大学（玉泉路）

2024秋季，研究生课程，《模式识别原理与方法》，中国科学院大学（雁栖湖）

2023秋季，本科生课程，《模式识别研讨课》，中国科学院大学（玉泉路）

2023秋季，研究生课程，《模式识别》，中国科学院大学（雁栖湖）

2022秋季，博士生课程，《模式识别与机器学习》，中国科学院自动化所

2022秋季，研究生课程，《模式识别》，中国科学院大学（雁栖湖）

2021秋季，博士生课程，《模式识别与机器学习》，中国科学院自动化所

2021秋季，研究生课程，《模式识别》，中国科学院大学（雁栖湖）

2020秋季，博士生课程，《模式识别与机器学习》，中国科学院自动化所

2020秋季，研究生课程，《模式识别》，中国科学院大学（雁栖湖）

2019秋季，博士生课程，《模式识别与机器学习》，中国科学院自动化所

2019秋季，研究生课程，《模式识别》，中国科学院大学（雁栖湖）

2018夏季，研究生课程，《深度学习在视觉和自然语言处理中的应用》，中国科学院大学（雁栖湖）

2018秋季，博士生课程，《模式识别与机器学习》，中国科学院自动化所

2018秋季，研究生课程，《模式识别》，中国科学院大学（雁栖湖）

2017夏季，研究生课程，《深度学习在视觉和自然语言处理中的应用》，中国科学院大学（雁栖湖）

2017秋季，博士生课程，《模式识别与机器学习》，中国科学院自动化所

2017秋季，研究生课程，《模式识别》，中国科学院大学（雁栖湖）

2016夏季，研究生课程，《深度学习》，中国科学院大学（雁栖湖）

奖励与荣誉

中国科学院青年创新促进会优秀会员，2024

小米青年学者，2023

科技创新2030新一代人工智能重大项目青年科学家，2022

朱李月华优秀教师奖，2021

吴文俊人工智能优秀青年奖，2020

中科院基础前沿研究计划从0到1原始创新项目，2019

中国科学院大学校级研究生优秀课程，2019

中国科学院青年创新促进会，2019

中国科协青年人才托举工程，2018 

中科院自动化所特聘青年骨干，2017

模式识别国家重点实验室优秀员工，2016

脑科学与智能技术卓越创新中心人才计划，2015

国家公派留学基金，2015

中国计算机学会优秀博士论文，2014

IEEE TPAMI焦点论文，2013

代表性论文

  • Haiyang Guo, Fanhu Zeng, Ziwei Xiang, Fei Zhu, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu. HiDe-LLaVA: Hierarchical decoupling for continual instruction tuning of multimodal large language model. ACL 2025.

  • Fanhu Zeng, Fei Zhu, Haiyang Guo, Xu-Yao Zhang, Cheng-Lin Liu. ModalPrompt: Towards efficient multimodal continual instruction tuning with dual-modality guided prompt. EMNLP 2025.

  • Haiyang Guo, Fanhu Zeng, Fei Zhu, Wenzhuo Liu, Da-Han Wang, Jian Xu, Xu-Yao Zhang, Cheng-Lin Liu. Federated continual instruction tuning. ICCV 2025.

  • Siqing Song, Chuang Wang, Ruiqi Wang, Yi Yang, Xu-Yao Zhang. Achieving binary weight and activation for LLMs using post-training quantization. ACL Findings 2025.

  • Fanhu Zeng, Zhen Cheng, Fei Zhu, Hongxin Wei, Xu-Yao Zhang. Local-prompt: Extensible local prompts for few-shot out-of-distribution detection. ICLR 2025.

  • Yi Chen, Jian Xu, Xu-Yao Zhang, Wen-Zhuo Liu, Yang-Yang Liu, Cheng-Lin Liu. Recoverable compression: A multimodal vision token recovery mechanism guided by text information. AAAI 2025.

  • Fei Zhu, Xu-Yao Zhang, Zhen Cheng, Cheng-Lin Liu. PASS++: A dual bias reduction framework for non-exemplar class-incremental learning. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2025.

  • Shijie Ma, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu. ProtoGCD: Unified and unbiased prototype learning for generalized category discovery. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2025. 

  • Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu. Average of pruning: Improving performance and stability of out-of-distribution detection. IEEE Trans. Neural Networks and Learning Systems (TNNLS), 2025.

  • Songze Li, Tonghua Su, Xu-Yao Zhang, Zhongjie Wang. Continual learning with knowledge distillation: A survey. IEEE Trans. Neural Networks and Learning Systems (TNNLS), 2025.

  • Jiao Zhang, Xiang Ao, Xu-Yao Zhang, Cheng-Lin Liu. Towards reliable domain generalization: Insights from the PF2HC benchmark and dynamic evaluations. Pattern Recognition, 2025. 

  • Shijie Ma, Fei Zhu, Zhen Cheng, Xu-Yao Zhang. Towards trustworthy dataset distillation. Pattern Recognition, 2025.

  • Shijie Ma, Fei Zhu, Zhun Zhong, Wenzhuo Liu, Xu-Yao Zhang, Cheng-Lin Liu. Happy: A debiased learning framework for continual generalized category discovery. NeurIPS 2024. 

  • Haiyang Guo, Fei Zhu, Wenzhuo Liu, Xu-Yao Zhang, Cheng-Lin Liu. PILoRA: Prototype guided incremental LoRA for federated class-incremental learning. ECCV 2024.

  • Shijie Ma, Fei Zhu, Zhun Zhong, Xu-Yao Zhang, Cheng-Lin Liu. Active generalized category discovery. CVPR 2024. 

  • Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu, Zhaoxiang Zhang. RCL: Reliable Continual Learning for Unified Failure Detection. CVPR 2024.

  • Zhengqing Gao, Xu-Yao Zhang, Cheng-Lin Liu. Unified entropy optimization for open-set test-time adaptation. CVPR 2024. 

  • Fei Zhu, Xu-Yao Zhang, Zhen Cheng, Cheng-Lin Liu. Revisiting confidence estimation: Towards reliable failure prediction. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2024.

  • Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu. Unified classification and rejection: A one-versus-all framework. Machine Intelligence Research, 2024.

  • Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu. Breaking the limits of reliable prediction via generated data. International Journal of Computer Vision (IJCV), 2024.

  • Yuqi Wang, Xu-Yao Zhang, Cheng-Lin Liu, Tieniu Tan, Zhaoxiang Zhang. Emergence of machine language: Towards symbolic intelligence with neural networks. National Science Review, 2024.

  • Yue Xu, Xu-Yao Zhang, Zhaoxiang Zhang, Cheng-Lin Liu. Large-scale continual learning for ancient Chinese character recognition. Pattern Recognition, 2024.

  • Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu. OpenMix: Exploring outlier samples for misclassification detection. CVPR 2023. 

  • Xu-Yao Zhang, Guo-Sen Xie, Xiuli Li, Tao Mei, Cheng-Lin Liu. A survey on learning to reject. Proceedings of the IEEE, 2023.

  • Fei Zhu, Xu-Yao Zhang, Rui-Qi Wang, Cheng-Lin Liu. Learning by seeing more classes. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2023.

  • Guo-Sen Xie, Xu-Yao Zhang, Tian-Zhu Xiang, Fang Zhao, Zheng Zhang, Ling Shao, Xuelong Li. Leveraging balanced semantic embedding for generative zero-shot learning. IEEE Trans. Neural Networks and Learning Systems (TNNLS), 2023.

  • Xiu-Chuan Li, Xiaobo Xia, Fei Zhu, Tongliang Liu, Xu-Yao Zhang, Cheng-Lin Liu. Dynamics-aware loss for learning with label noise. Pattern Recognition, 2023.

  • Jiao Zhang, Xu-Yao Zhang, Chuang Wang, Cheng-Lin Liu. Deep representation learning for domain generalization with information bottleneck principle, Pattern Recognition, 2023.

  • Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu. Imitating the oracle: Towards calibrated model for class incremental learning. Neural Networks, 2023.

  • Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu. Adversarial training with distribution normalization and margin balance, Pattern Recognition, 2023.

  • Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu. Rethinking confidence reliability for failure prediction. ECCV 2022. 

  • Hong-Ming Yang, Xu-Yao Zhang, Fei Yin, Qing Yang, Cheng-Lin Liu. Convolutional prototype network for open set recognition. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2022.

  • Xiang Ao, Xu-Yao Zhang, Cheng-Lin Liu. Cross-modal prototype learning for zero-shot handwritten character recognition. Pattern Recognition, 2022.

  • Xiu-Chuan Li, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Decision-based adversarial attack with frequency mixup. IEEE Trans. Information Forensics and Security (TIFS), 2022.

  • Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu. Class-incremental learning via dual augmentation. NeurIPS 2021. 

  • Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin, Cheng-Lin Liu. Prototype augmentation and self-supervision for incremental learning. CVPR 2021. 

  • Guo-Sen Xie, Xu-Yao Zhang, Yazhou Yao, Zheng Zhang, Fang Zhao, Ling Shao. VMAN: A virtual mainstay alignment network for transductive zero-shot learning. IEEE Trans. Image Processing (TIP), 2021.

  • Xu-Yao Zhang, Cheng-Lin Liu, Ching Y. Suen. Towards robust pattern recognition: A review. Proceedings of the IEEE, 2020.

  • Wenhao He, Xu-Yao Zhang, Fei Yin, Zhenbo Luo, Jean-Marc Ogier, Cheng-Lin Liu. Realtime multi-scale scene text detection with scale-based region proposal network. Pattern Recognition, 2020.

  • Xiao-Bo Jin, Xu-Yao Zhang, Kaizhu Huang, Guang-Gang Geng. Stochastic conjugate gradient algorithm with variance reduction. IEEE Trans. Neural Networks and Learning Systems (TNNLS), 2019.

  • Hong-Ming Yang, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Robust classification with convolutional prototype learning. CVPR 2018.

  • Wenhao He, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Multi-oriented and multi-lingual scene text detection with direct regression. IEEE Trans. Image Processing (TIP), 2018.

  • Xu-Yao Zhang, Fei Yin, Yan-Ming Zhang, Cheng-Lin Liu, Yoshua Bengio. Drawing and recognizing Chinese characters with recurrent neural network. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2018.

  • Wenhao He, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Deep direct regression for multi-oriented scene text detection. ICCV 2017.

  • Guo-Sen Xie, Xu-Yao Zhang, Shuicheng Yan, Cheng-Lin Liu. SDE: A novel selective, discriminative and equalizing feature representation for visual recognition. International Journal of Computer Vision (IJCV), 2017.

  • Guo-Sen Xie, Xu-Yao Zhang, Shuicheng Yan, Cheng-Lin Liu. Hybrid CNN and dictionary-based models for scene recognition and domain adaptation. IEEE Trans. Circuits and Systems for Video Technology (TCSVT), 2017.

  • Xu-Yao Zhang, Guo-Sen Xie, Cheng-Lin Liu, Yoshua Bengio. End-to-end online writer identification with recurrent neural network. IEEE Trans. Human-Machine Systems (THMS), 2017.

  • Xu-Yao Zhang, Yoshua Bengio, Cheng-Lin Liu. Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark. Pattern Recognition, 2017.

  • Ming-Ke Zhou, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. Discriminative quadratic feature learning for handwritten Chinese character recognition. Pattern Recognition, 2016.

  • Xu-Yao Zhang, Lingfeng Wang, Shiming Xiang, Cheng-Lin Liu. Retargeted least squares regression algorithm. IEEE Trans. Neural Networks and Learning Systems (TNNLS), 2015.

  • Xu-Yao Zhang, Kaizhu Huang, Cheng-Lin Liu. Feature transformation with class conditional decorrelation. ICDM 2013.

  • Xu-Yao Zhang, Cheng-Lin Liu. Locally smoothed modified quadratic discriminant function. ICDAR 2013.

  • Xu-Yao Zhang, Cheng-Lin Liu. Evaluation of weighted Fisher criteria for large category dimensionality reduction in application to Chinese handwriting recognition. Pattern Recognition, 2013.

  • Xu-Yao Zhang, Cheng-Lin Liu. Writer adaptation with style transfer mapping. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2013.

  • Xu-Yao Zhang, Kaizhu Huang, Cheng-Lin Liu. Pattern field classification with style normalized transformation. IJCAI 2011.

  • Xu-Yao Zhang, Cheng-Lin Liu. Style transfer matrix learning for writer adaptation. CVPR 2011.