基本信息

张一帆 研究员 博士生导师 中国科学院自动化研究所

复杂系统认知与决策重点实验室、模式识别国家重点实验室

高效智能计算与学习团队（团队负责人：程健研究员）

电子邮件： yfzhang AT nlpr.ia.ac.cn

通信地址： 北京市海淀区中关村东路95号

邮政编码： 100190

团队主页：https://clab.ia.ac.cn/

现为中国科学院自动化研究所研究员、博导、中国科学院大学岗位教授，中国科学院大学南京学院信息学院副院长。主要从事视觉内容分析与高效计算、机器学习、AI4S等方面的研究。主持多项国家自然科学基金项目、科技部2030新一代人工智能重大项目课题、中科院先导A类专项课题、企业委托项目。在IEEE T-PAMI、IEEE T-IP、 IEEE T-CYB、 IEEE T-MM等权威国际期刊和NeurIPS、ICML、CVPR、ICCV、ECCV等顶级国际会议上发表论文六十余篇。中国计算机学会计算机视觉专委会委员，中国图象图形学学会机器视觉专委会委员，AVS标准工作组数字媒体内容描述组组长，IEEE1857.6标准工作组组长。中科院院长奖获得者，中科院青年创新促进会成员，中科院特聘研究骨干。

研究领域

视觉内容分析与高效计算、具身智能

AI for science、科学智能计算、神经组合优化

机器学习（包括深度学习、强化学习、图模型等）

招生信息


招生专业
081104-模式识别与智能系统
081203-计算机应用技术
招生方向
图像与视频处理，视觉内容分析与高效计算
机器学习
智能决策
招生要求

专业背景不限。但希望你对科研怀有强烈的兴趣和追求卓越的精神，具备良好的数学基础、编程能力以及自主学习能力。 
由于招生数量有限，希望提前与我联系。 
另招收少量实习生，要求计算机相关专业的在读本科或研究生，具有较强的编程能力，实习期半年以上者优先。

教育背景

2004-09--2010-01   中国科学院自动化研究所   博士
2000-09--2004-06   东南大学自动控制系   学士

工作经历


工作简历

2020.10~至今，中国科学院自动化研究所  模式识别国家重点实验室,  研究员 

2014.10~2020.09，中国科学院自动化研究所 模式识别国家重点实验室,  副研究员 

2011.05~2012.07，美国伦斯勒理工学院(RPI)  电子计算机工程系,  访问学者 

2010.06~2014.09，中国科学院自动化研究所 模式识别国家重点实验室,  助理研究员

荣誉与奖励

2025年 获得中国图象图形学学会自然科学一等奖

2020年 获得ECCV AIM挑战赛Learned ISP比赛冠军 

2019年 获得NeurIPS神经网络压缩与加速竞赛ImageNet和CIFAR-100两项任务冠军 

2019年 获得ICCV轻量化人脸识别比赛亚军和快速人脸识别比赛亚军 

2018年 获得中国图象图形学学会科学技术二等奖 

2018年 获得PRCV2018美图短视频实时分类挑战赛冠军

2018年 获得“AI Challenger”全球AI挑战赛短视频实时分类比赛亚军 

2016年 获得“CCF-腾讯犀牛鸟基金”

2014年 入选“中国科学院青年创新促进会”

2010年 获得“中国科学院院长优秀奖”

‍‍​

出版信息

Selected Articles:

  1. Shengda Gu, Kai Li, Junliang Xing, Yifan Zhang, Jian Cheng. Evolutionary Augmented Reinforcement Learning for Neural Combinatorial Optimization. IEEE Transactions on Evolutionary Computation, 2026.
  2. Boxiao Wang, Kai Li, Tianyi Liu, Chen Li, Junzhe Wang, Yifan Zhang, Jian Cheng. LLM-based Scientific Equation Discovery via Physics-informed Token-Regularizied Policy Optimization. The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026.
  3. Y. Wu, J. Pan, Y. Zhang, N. Xu, F. Zeng, J. Cheng, ‍‍"RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience," I‍‍n Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.
  4. Y. Huang, Y. Zhang, J. Cheng, ‍‍"Optimal Transport–Guided Stochastic Control for Graph Combinatorial Optimization," I‍‍n Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.
  5. R. Jia, J. Zhang, Y. Zhang, J. Cheng, ‍‍"Preference-Modulated Structural Attention for Multi-Objective Combinatorial Optimization," I‍‍n Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.
  6. J. He, K. Li, X. Dong, Y. Zang, Y. Jing, Y. Zhang, J. Xing, J. Cheng, ‍‍"HyMTRL: A Hybrid Multi-Task Reinforcement Learning Framework via Phased Policy Evolution," I‍‍n Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.
  7. X. Ke, K. Li, J. Xing, Y. Zhang, J. Cheng, ‍‍"Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery," I‍‍n Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026.
  8. H Ding, Z Xu, Y Fang, Y Wu, Z Chen, J Shi, J Huo, Y Zhang, Y Gao, "LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments," IEEE International Conference on Robotics and Automation (ICRA), 2026.
  9. J. Zhang, J. He, Y. Zhang, Y. Zang, N. Xu, and J. Cheng, "Bi-Level Knowledge Transfer for Multi-Task Multi-Agent Reinforcement Learning," In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2025.
  10. Y. Wu, Y. Zhang, Y. Wu, Y. Wang, J. Zhang, and J. Cheng, "Training LLMs for Optimization Modeling via Iterative Data Synthesis and Structured Validation," In Findings of the Association for Computational Linguistics: EMNLP, 2025.
  11. Z. Li, Q. Hu, Y. Chen, P. Wang, Y. Zhang, and Jian Cheng, "LoRaDA: Low-Rank Direct Attention Adaptation for Efficient LLM Fine-tuning,"  In Findings of the Association for Computational Linguistics: EMNLP, 2025.
  12. Y. Yu, C. Cao, Y. Zhang, and Y. Zhang, "Learning to Generalize without Bias for Open-Vocabulary Action Recognition," In Proceedings of IEEE International Conference On Computer Vision (ICCV), 2025.
  13. Y. Wu, Y. Zhang, Z. Liang, and J. Cheng, ‍‍"HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming," I‍‍n Proceedings of the 41st International Conference on Machine Learning (ICML), 2024.
  14. J. Zhang, Y. Zhang, X. Zhang, Y. Zang, and J. Cheng, "Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning," In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2024.
  15. ‍‍Y. Lu, C. Cao Y. Zhang, and Y. Zhang, "Learnable Locality-Sensitive Hashing for Video Anomaly Detection" IEEE Transactions on Circuits Systems and Video Technology (T-CSVT), Vol. 33, No. 2, pp. 963-976, 2023.‍
  16. S. Liu, X. Zhang, Y. Li, Y. Zhang and J. Cheng, "On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning," In Proceedings of the Eleventh International Conference on Learning Representations (ICLR), 2023.
  17. L. Sun, Y. Zhang, J. Cheng and H. Lu,"Asynchronous Event Processing with Local-Shift Graph Convolutional Network," In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.
  18. L. Shi, Y. Zhang, J. Cheng, and H. Lu, "Action recognition via pose-based graph convolutional networks with intermediate dense supervision," Pattern Recognition (PR), Vol. 121, Col. 108170, 2022.
  19. W. Cao, Y. Zhang, J. Gao, A. Cheng, K. Cheng and J. Cheng,"PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient," In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2022. (Spotlight)
  20. ‍‍L. Sun, Y. Zhang, K. Cheng, J. Cheng and H. Lu,"MENet: a Memory-based network with Dual-branch for Efficient Event Stream Processing," In Proceedings of the European Conference on Computer Vision (ECCV), 2022.‍‍
  21. ‍‍H. Gao, Y. Zhang, L. Sun and J. Cheng, "Action Representing by Constrained Conditional Mutual Information," In Proceedings of the Asian conference on computer vision (ACCV), 2022.‍‍
  22. ‍‍K. Cheng, Y. Zhang, X. He, J. Cheng, and H. Lu, "Extremely Lightweight Skeleton-Based Action Recognition With ShiftGCN++," IEEE Transactions on Image Processing (T-IP) Vol. 30, pp. 7333-7348, 2021.‍
  23. ‍‍‍‍L. Shi, Y. Zhang, J. Cheng and H. Lu, ‍‍"AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition,"  In Proceedings of IEEE International Conference On Computer Vision (ICCV), 2021.
  24. Y. Zhang, L. Shi, Y. Wu, K. Cheng, J. Cheng and H. Lu, "Gesture Recognition Based on Deep Deformable 3D Convolutional Neural Networks," Pattern Recognition (PR), Vol. 107, 2020.
  25. L. Shi, Y. Zhang, J. Cheng and H. Lu, "Skeleton-Based Action Recognition With Multi-Stream Adaptive Graph Convolutional Networks," IEEE Transactions on Image Processing (T-IP) Vol. 29, pp. 9532-9545, 2020.
  26. Q. Chen, P. Wang, A. Cheng, W. Wang, Y. Zhang and Jian Cheng, "Robust one-stage object detection with location-aware classifiers.," Pattern Recognition (PR), Vol. 105, Col. 107334, 2020.
  27. K. Cheng, Y. Zhang, C. Cao, L. Shi, J. Cheng and H. Lu, "Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition, In Proceedings of European Conference on Computer Vision (ECCV), 2020.
  28. K. Cheng, Y. Zhang, X. He, W. Chen, J. Cheng and H. Lu, "Skeleton-Based Action Recognition with Shift Graph Convolutional Network," in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, US, 2020. (Oral)
  29. C. Cao, C. Lan, Y. Zhang, W. Zeng, H. Lu and Y. Zhang, "Skeleton-Based Action Recognition With Gated Convolutional Neural Networks," IEEE Transactions on Circuits Systems and Video Technology (T-CSVT), Vol. 29, No. 11, pp. 3247-3257, 2019.
  30. L. Shi, Y. Zhang, J. Cheng and H. Lu, "Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition," In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Long beach, US, 2019.
  31. L. Shi, Y. Zhang, J. Cheng and H. Lu, "Skeleton-Based Action Recognition with Directed Graph Neural Networks," In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Long beach, US, 2019.
  32. Y. Zhang, C. Cao, J. Cheng and H. Lu, “EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition,” IEEE Transactions on Multimedia(T-MM), Vol. 20, No. 5, pp. 1038-1050, 2018.
  33. C. Cao, Y. Zhang, C. Zhang and H. Lu, “Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition,” IEEE Transactions on Cybernetics(T-CYB), Vol. 48, No. 3, pp. 1095-1108, 2018.
  34. P. Wang, Q. Hu, Y. Zhang, C. Zhang, Y. Liu and J. Cheng, "Two-Step Quantization for Low-bit Neural Networks," in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, US, 2018.
  35. Q. Hu, G. Li, P. Wang, Y. Zhang and J Cheng: Training Binary Weight Networks via Semi-Binary Decomposition. In Proceedings of the European conference on computer vision (ECCV), 2018: 657-673.
  36. C. Cao, Y. Zhang, Y. Wu, H. Lu and J. Cheng, "Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks with Spatiotemporal Transformer Modules,"  In Proceedings of IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017. (Spotlight)
  37. Q. Hu, J. Wu, L. Bai, Y. Zhang and J. Cheng, "Fast K-means for Large Scale Clustering," In Proceedings of ‍‍International Conference on Information and Knowledge Management (‍‍CIKM) 2017: 2099-2102.
  38. Y. Zhang, Z. Tang, B. Wu, Q. Ji, and H. Lu, “A Coupled Hidden Conditional Random Field Model for Simultaneous Face Clustering and Naming in Videos,” IEEE Transactions on Image Processing (T-IP), Vol. 25, No. 12, pp. 5780-5792, 2016.
  39. C. Cao, Y. Zhang, C. Zhang and H. Lu, “Action Recognition with Joints-Pooled 3D Deep Convolutional Descriptors”, In Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI), 2016.
  40. Z. Tang, Y. Zhang, Z. Li and H. Lu, “Face clustering in videos with proportion prior”, In Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI), Buenos Aires, Argentina, 2015 (Oral).
  41. C. Cao, Y. Zhang and H. Lu,“Multi-modal learning for gesture recognition”, In Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Torino, Italy, 2015.
  42. C. Cao, Y. Zhang and H. Lu “Spatio-Temporal Triangular-Chain CRF for Activity Recognition”, In Proceedings of ACM Multimedia 2015: 1151-1154.
  43. Z. Tang, Y. Zhang, S. Qiu and H. Lu, “Video Face Naming Using Global Sequence Alignment,” In proceedings of IEEE International Conference on Image Processing (ICIP), Paris, France, 2014.
  44. Y. Zhang, Q. Ji and H. Lu, “Event Detection in Complex Scene Using Interval Temporal Constraints,” In Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 3184-3191, Sydney, Australia, 2013.
  45. B. Wu, Y. Zhang, B. Hu and Q. Ji, “Constrained Clustering and Its Application to Face Clustering In Videos," In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Portland, US, 2013.
  46. Y. Zhang, Y. Zhang, E. Swears, N. Lario, Z. Wang and Q. Ji, “Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), Vol. 35, No. 10, pp. 2468-2483, Oct. 2013.
  47. Y. Zhang, C. Xu, H. Lu and Y. Huang, “Character Identification in Feature-length Films Using Global Face-Name Matching,” IEEE Transactions on Multimedia (T-MM), Vol. 11, No. 7, pp. 1276-1288, 2009.
  48. C. Xu, Y. Zhang, G. Zhu, Y. Rui, H. Lu and Q. Huang, “Using Web-cast Text for Semantic Event Detection in Broadcast Sports Video,” IEEE Transactions on Multimedia (T-MM), Vol. 10, No. 7, pp. 1342-1355, Nov. 2008.

科研活动

科研项目

  1. 科技部2030“新一代人工智能”重大项目课题，“力学数据智能分析与建模工具集”，2025.06-2030.05，负责人。
  2. 中国科学院先导A类专项课题，“离散优化智能求解工具”，2025.02-2027.01，负责人。
  3. 科技部2030“新一代人工智能”重大项目子课题，“神经网络表示与压缩标准”，2019.12-2022.12，负责人。
  4. 国家自然科学基金，“基于深度时空建模的人体动作识别”，2019.01-2022.12, 负责人。
  5. 国家自然科学基金，“基于概率图模型的复杂行为识别”，2016.01-2019.12, 负责人。
  6. 国家自然科学基金，“知识与数据混合驱动的概率图模型研究及在行为识别的应用”，2013.01-2015.12, 负责人。
  7. 中国科学院青促会人才项目， 2014.07-2017.12, 负责人。
  8. 中国科学院院长奖项目，2011.04-2012.12，负责人。

‍‍‍‍‍‍‍‍

指导学生

现指导学生：

黄洋   博士研究生  081104-模式识别与智能系统  

刘秉运  硕士研究生  085410-人工智能  

王润翔  博士研究生  081100-控制科学与工程  

周世辰  博士研究生  081100-控制科学与工程  

许成林  硕士研究生  085410-人工智能  

梁振兴  博士研究生  081104-模式识别与智能系统  

唐桢骅  硕士研究生  085410-人工智能  

廖谂韬  硕士研究生  085410-人工智能  

潘俊燃  博士研究生  081104-模式识别与智能系统  

曾凡硕  硕士研究生  081104-模式识别与智能系统  


联合指导学生：

徐宁 博士研究生

丁泓宇 博士研究生 

丁星宇 博士研究生 

贾荣盛 博士研究生 

武希举 博士研究生 


毕业生去向：

曹聪琦 博士 西北工业大学准聘副教授

史磊 博士 美团

程科 博士 美团

唐志强 硕士 Rutgers University 读博

李耀宇 硕士 自动化所读博

李玉惠 硕士 歌尔声学

孙琳晖 博士 美团

高浩元 硕士 上海交通大学读博

梁恬 硕士 浙江大学读博

刘丰源 硕士 济南市交通局

曹巍瀚 硕士 上海人工智能实验室

张天 硕士 武汉大学读博

曹婕 硕士 长沙市科技局

赵士云 硕士 北京通用人工智能研究院

刘宇鸣 硕士 华为

吴洋 博士 字节跳动

张峻凯 博士 腾讯