多模态大模型，具身智能，强化学习

招收硕士研究生

081203-计算机应用技术

多模态大模型
具身智能
强化学习

2013-09--2019-07   中国科学院计算技术研究所   工学博士
2009-09--2013-07   北京航空航天大学   理学学士

   

2021-10~现在, 中国科学院计算技术研究所, 副研究员
2019-07~2021-09,中国科学院计算技术研究所, 助理研究员

   

（ 1 ） 一种基于二值神经网络的图像分类方法及系统, 发明专利, 2022, 第 1 作者, 专利号: CN113936169A

（ 2 ） 基于迁移学习的人物检测方法和系统, 发明专利, 2022, 第 1 作者, 专利号: CN113936295A

（ 3 ） 基于在线域自适应深度学习的图片分类方法及系统, 发明专利, 2022, 第 2 作者, 专利号: CN113936168A

（ 4 ） 一种基于联合聚类域自适应的图片分类方法和系统, 发明专利, 2022, 第 1 作者, 专利号: CN113936167A

（ 5 ） 基于特征图恢复的场景分割方法和系统, 专利授权, 2020, 第 2 作者, 专利号: CN109034198B

（ 6 ） 融合全局信息的场景分割修正方法与系统, 专利授权, 2018, 第 2 作者, 专利号: CN107564007A

（ 7 ） 融合局部信息的场景分割修正方法与系统, 发明专利, 2018, 第 2 作者, 专利号: CN107564013A

   

[1] Peng Wei Jin, Yunji Chen. Online Symbolic Regression with Informative Query. AAAI Conference on Artificial Intelligence (AAAI). 2023, 
[2] Yi, Qi, Zhang, Rui, Peng, Shaohui, Guo, Jiaming, Hu, Xing, Du, Zidong, Guo, Qi, Chen, Ruizhi, Li, Ling, Chen, Yunji. Learning controllable elements oriented representations for reinforcement learning. NEUROCOMPUTING[J]. 2023, 第 2 作者549: http://dx.doi.org/10.1016/j.neucom.2023.126455.
[3] QI Yi, Yunji Chen. Online Prototype Alignment for Few-shot Policy Transfer. International Conference on Minority Languages (ICML XVI). 2023, 
[4] Shaohui Peng, Xing Hu, Rui Zhang, Jiaming Guo, Qi Yi, Ruizhi Chen, Zidong Du, Ling Li, Qi Guo, Yunji Chen. Conceptual Reinforcement Learning for Language-Conditioned Tasks. AAAI Conference on Artificial Intelligence (AAAI). 2023, 第 3 作者https://arxiv.org/abs/2303.05069.
[5] 郭家明, 张蕊, 支天, 何得园, 黄迪, 常明, 张曦珊, 郭崎. 硬件感知的高效特征融合网络搜索. 计算机学报. 2022, 第 2 作者45(11): 2420-2432, http://lib.cqvip.com/Qikan/Article/Detail?id=7108376306.
[6] Tianyi Wu, Sheng Tang, Rui Zhang, Guodong Guo. Consensus Feature Network for Scene Parsing. IEEE Transactions on Multimedia(CCF B类多媒体领域国际顶刊，通讯作者)[J]. 2022, 第 3 作者24: 3208-3217, https://ieeexplore.ieee.org/document/9473001.
[7] Yi, Qi, Zhang, Rui, Peng, Shaohui, Guo, Jiaming, Hu, Xing, Du, Zidong, Zhang, Xishan, Guo, Qi, Chen, Yunji. Object-Category Aware Reinforcement Learning. NeurIPS 2022. 2022, 第 2 作者http://arxiv.org/abs/2210.07802.
[8] Wen, Yuanbo, Qi Guo, Du, Zidong, Xu, Jianxing, Zhang, Zhenxing, Xing Hu, Wei Li, Rui Zhang, Chao Wang, Zhou Xuehai, Chen, Tianshi. Enabling One-Size-Fits-All Compilation Optimization for Inference Across Machine Learning Computers. IEEE TRANSACTIONS ON COMPUTERS[J]. 2022, 第 8 作者71(9): 2313-2326, http://dx.doi.org/10.1109/TC.2021.3128266.
[9] Peng, Shaohui, Hu, Xing, Zhang, Rui, Tang, Ke, Guo, Jiaming, Yi, Qi, Chen, Ruizhi, Zhang, Xishan, Du, Zidong, Li, Ling, Guo, Qi, Chen, Yunji. Causality-driven Hierarchical Structure Discovery for Reinforcement Learning. NeurIPS 2022. 2022, 第 3 作者http://arxiv.org/abs/2210.06964.
[10] Liu, Chang, Zhang, Xishan, Zhang, Rui, Li, Ling, Zhou, Shiyi, Huang, Di, Li, Zhen, Du, Zidong, Liu, Shaoli, Chen, Tianshi. Rethinking the Importance of Quantization Bias, Toward Full Low-Bit Training. IEEE Transactions on Image Processing[J]. 2022, 第 3 作者31: 7006-7019, http://dx.doi.org/10.1109/TIP.2022.3216776.
[11] Huang, Di, Zhang, Rui, Zhang, Xishan, Wu, Fan, Wang, Xianzhuo, Jin, Pengwei, Liu, Shaoli, Li, Ling, Chen, Yunji. A Decomposable Winograd Method for N-D Convolution Acceleration in Video Analysis. INTERNATIONAL JOURNAL OF COMPUTER VISION[J]. 2021, 第 2 作者  通讯作者  129(10): 2806-2826, http://dx.doi.org/10.1007/s11263-021-01500-9.
[12] Du, Zhixing, Zhang, Rui, Chang, Ming, Zhang, Xishan, Liu, Shaoli, Chen, Tianshi, Chen, Yunji. Distilling Object Detectors with Feature Richness. 2021, 第 2 作者http://arxiv.org/abs/2111.00674.
[13] Wang, Yu, Zhang, Rui, Zhang, Shuo, Li, Miao, Xia, YangYang, Zhang, XiShan, Liu, ShaoLi. Domain-Specific Suppression for Adaptive Object Detection. 2021, 第 2 作者http://arxiv.org/abs/2105.03570.
[14] Guo, Jiaming, Zhang, Rui, Zhang, Xishan, Peng, Shaohui, Yi, Qi, Du, Zidong, Hu, Xing, Guo, Qi, Chen, Yunji. Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment. 2021, 第 2 作者http://arxiv.org/abs/2107.12216.
[15] Tianyi Wu, Sheng Tang, Rui Zhang, Juan Cao, Yongdong Zhang. CGNet: A Light-Weight Context Guided Network for Semantic Segmentation. IEEE Transactions on Image Processing[J]. 2021, 第 3 作者30: 1169-1179, 
[16] Zhang, Xishan, Liu, Shaoli, Zhang, Rui, Liu, Chang, Huang, Di, Zhou, Shiyi, Guo, Jiaming, Guo, Qi, Du, Zidong, Zhi, Tian, Chen, Yunji, IEEE. Fixed-Point Back-Propagation Training. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR). 2020, 第 3 作者2327-2335, 
[17] 张蕊, 李锦涛. 基于深度学习的场景分割算法研究综述. 计算机研究与发展[J]. 2020, 第 1 作者57(4): 859-875, https://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFQ&dbname=CJFDLAST2020&filename=JFYZ202004016&v=MzAwNDdlWnVkdUZ5cmtWNzNKTHl2U2RMRzRITkhNcTQ5RVlvUjhlWDFMdXhZUzdEaDFUM3FUcldNMUZyQ1VSN3E=.
[18] Li, Yu, Tang, Sheng, Zhang, Rui, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng. Asymmetric GAN for Unpaired Image-to-Image Translation. IEEE Transactions on Image Processing(CCF A类图像处理国际顶刊，通讯作者)[J]. 2019, 第 3 作者28(12): 5881-5896, http://doi.org/10.1109/TIP.2019.2922854.
[19] Tianyi Wu, Sheng Tang, Rui Zhang, Juan Cao, Jintao Li. Tree-Structured Kronecker Convolutional Network for Semantic Segmentation. IEEE ICME 2019. 2019, 第 3 作者940-945, 
[20] Zhang, Rui, Tang, Sheng, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng. Perspective-Adaptive Convolutions for Scene Parsing. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE[J]. 2019, 第 1 作者42(4): 909-924, http://dx.doi.org/10.1109/TPAMI.2018.2890637.
[21] Li, Yu, Tang, Sheng, Zhang, Rui, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng. Asymmetric GAN for Unpaired Image-to-Image Translation. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 第 3 作者28(12): 5881-5896, http://dx.doi.org/10.1109/TIP.2019.2922854.
[22] Zhang Rui, Tang Sheng, Liu Luoqi, Zhang, Yongdong, Li Jintao, Yan, Shuicheng. High Resolution Feature Recovering for Accelerating Urban Scene Parsing. The 27th International Joint Conference on Artificial Intelligence (IJCAI-2018), Stockholm, Sweden, July 13-19, 2018(CCF A类人工智能国际顶级会议长文, 通讯作者)[J]. 2018, 第 1 作者
[23] Zhang, Rui, Tang, Sheng, Li, Yu, Guo, Junbo, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng, ACM. Style Separation and Synthesis via Generative Adversarial Networks. PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18). 2018, 第 1 作者183-191, http://dx.doi.org/10.1145/3240508.3240524.
[24] Zhang, Rui, Tang, Sheng, Liu, Wu, Zhang, Yongdong, Li, Jintao. Multi-modal tag localization for mobile video search. MULTIMEDIA SYSTEMS[J]. 2017, 第 1 作者23(6): 713-724, http://dx.doi.org/10.1007/s00530-016-0506-9.
[25] Zhang, Rui, Tang, Sheng, Zhang, Yongdong, Li, Jintao, Yan, Shuicheng, IEEE. Scale-adaptive Convolutions for Scene Parsing. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV). 2017, 第 1 作者2050-2058, 
[26] Zhang Rui, Tang Sheng, Li Min, Li Jintao, Yan Shuicheng. Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions. The 26th International Joint Conference on Artificial Intelligence (IJCAI-2017),Pages:3427-3433,Melbourne, Australia, August 19-25, 2017. (CCF A类人工智能国际顶级会议长文，通讯作者)[J]. 2017, 第 1 作者

（1） 智能计算系统实验教程, 机械工业出版社, 2021-08, 第 4 作者

   

（ 1 ） 基于神经网络结构和训练超参数联合搜索的自动机器学 习技术研究, 负责人, 国家任务, 2022-01--2024-12