计算机视觉、大模型相关的AI智能感知算法模型优化与加速，软硬件协同的AI模型压缩与计算架构研究，VLSI/SoC数字集成电路与AI智能芯片、智能系统设计等。

刘龙军，副教授，博导。2015年毕业于西安交通大学模式识别与智能系统专业，获工学博士学位，博士期间赴美国佛罗里达大学（University of Florida，UF）国家公派联合培养两年。在人工智能、集成电路设计、智能系统体系架构等领域期刊会议上如TPDS,TCS-I,TCSVT,TMM,TNNLS,ISCA,CVPR,AAAI,ACM MM等发表多篇论文。获得中国自动化学会“CAA自然科学奖”一等奖（“从芯片到系统的高效智能计算架构关键技术研究”，第二完成人）；高等教育（研究生）国家级教学成果一等奖（“价值塑造、前沿引领、产教融合、团队协同的人工智能高层次人才培养新体系”）；获得IEEE Computer Architecture Letter（IEEE计算机体系结构快报，第一作者）期刊年度最佳论文奖“Best of CAL”；以第一作者投稿的学术论文获得计算机体系结构领域国际顶级学术会议IEEE/ACM International Symposium on Computer Architecture（ISCA，IEEE/ACM国际计算机体系结构学术年会,第一作者）收录并在大会上做论文口述报告。获得IEEE International Conference on ASIC（IEEE国际专用集成电路设计学术会议）“优秀学生论文奖”（第一作者）。中国自动化学会科普奖“CAA科普奖”（“AI科普行动”）等等，承担国家自然科学基金、国家重点研发计划、国家科技重大专项“核高基”等多个项目。

国家自然科学基金、国家重点研发计划、国家重大科技专项、国家博士后基金、陕西省基金、中国工程院咨询项目、研究所横向项目等。

近年指导研究生发表的部分学术论文：(注:Longjun Liu*表示作为通信作者指导本人学生作为一作发表的论文)

Haonan Zhang, Longjun Liu*, Yuqi Huang, YangZhao, Xinyu Lei, et,al., “CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection”[C], IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024  (CCF A类).

Haonan Zhang, Longjun Liu*, Yi Zhang, Xinyu Lei, et,al., “DenseKD: Dense Knowledge Distillation by Exploiting Region and Sample Importance”[J], IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024 .

Xinyu Lie, Longjun Liu*, Yi Zhang, Haonan Zhang, “Self-supervised Learning Strategy Inspired by the Relationship Between Infant Cognition and Unsupervised Learning”[J], IEEE Transactions on Cognitive and Developmental Systems (TCDS), 2024.

Xinyu Lie, Longjun Liu*, Puhang Jia, Haoteng Li, et,al., “Low-light Infrared and Visible Image Fusion with Imbalanced Thermal Radiation Distribution”[J], IEEE Transactions on Instrumentation and Measurement(TIM), 2024.

Haonan Zhang, Longjun Liu*, Yuqi Huang, Xinyu Lei, et,al., “InstKD: Towards lightweight 3D object detection with instance-aware knowledge distillation”[J], IEEE Transactions on Intelligent Vehicles (TIV), 2024.

Xiaoqing Zhao, Longjun Liu*, Hongbin Sun, Nanning Zheng, et,al.,  “Compensation Architecture to Alleviate Noise Effects in RRAM-based Computing-in-memory Chips with Residual Resource”[C], The 57th IEEE International Symposium on Circuits and Systems (ISCAS), 2024.

Hongyi He, Longjun Liu*, Haonan Zhang, Nanning Zheng. “IS-DARTS: Stablizing DARTS through Presice Measurement on Candidate Importance”[C], The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024  (CCF A类).

Xinyu Lei, Longjun Liu*, Yi Zhang, Puhang Jia, Haonan Zhang et al., “RepCo: Replenish Sample Views with Better Consistency for Contrastive Learning”[J], Neural Networks , 2023.

Yi Zhang, Yingke Gao, Haonan Zhang, Xinyu Lei, Longjun Liu*. “Cross-layer Patch Alignment and Intra-and-inter Patch Relations for Knowledge Distillation”[C], IEEE International Conference on Image Processing (ICIP) , 2023.

Xiao Wang, Xiaodong Deng, Yingxiang Li, Shitao Chen, Longjun Liu*, Nanning Zheng. “Design Hybrid Computing Architecture for Accelerating Point Cloud Registration”[C], IEEE Intelligent Vehicles Symposium (IV) , 2023.

Yingxiang Li, Zhiwen Su, et al, Longjun Liu*. “FPGA Accelerated Real-time Recurrent All-Pairs Field Transforms for Optical Flow”[C], Chinese Automation Congress (CAC), 2022.

Shijie Wang, Xiaodong Deng, et al, Longjun Liu*. “FPGA-based Acceleration of Structured Light Depth Estimation", [C], Chinese Automation Congress (CAC), 2022.

Shuang Liu, Zhicheng Liu, et al, Longjun Liu*. “Design Compact YOLO based Network for Small Target Detection on Infrared Image”[C], Chinese Automation Congress (CAC), 2022.

Haonan Zhang, Longjun Liu*, Bingyao Kang, Nanning Zheng. “Hierarchical Model Compression via Shape-Edge Representation of Feature Maps -- an Enlightenment from the Primate Visual System”[J], IEEE Transactions on Multimedia (TMM) , 2022.

Hengyi Zhou, Hongyi He, Wancheng Liu, Yuhai Li, Haonan Zhang, Longjun Liu*. “A Novel Differentiable Mixed-Precision Quantization Search Framework for Alleviating the Matthew Effect and Improving Robustness”[C], The 14th Asian Conference on Machine Learning (ACML) , 2022.

Hengyi Zhou, Longjun Liu*, Haonan Zhang, Nanning Zheng. “Rethinking the Mechanism of the Pattern Pruning and the Circle Importance Hypothesis”[C], 30th ACM International Conference on Multimedia (ACM MM), 2022. (CCF A类) 

Hengyi Zhou, Longjun Liu*, Haonan Zhang, Hongyi He, Nanning Zheng. “CMB: A Novel Structural Re-parameterization Block without Extra Training Parameters”[C], International Joint Conference on Neural Networks (IJCNN), 2022.

Shaofei Yang, Longjun Liu, Jiantao Zhou, Yunfu Zhao, Gengxin Hua, Hongbin Sun, Nanning Zheng. “Robust and Efficient Star Identification Algorithm based on 1D Convolutional Neural Network” [J], IEEE Transactions on Aerospace and Electronic Systems (T-AES), 2022.

Haonan Zhang, Longjun Liu*, Hengyi Zhou, Liang Si, Hongbin Sun, Nanning Zheng. “Exploring the Discriminative Feature and Feature Correlation of Feature Maps for Hierarchical DNN Pruning and Compression”[J],  IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2022. 

Liang Si, Yuhai Li, Hengyi Zhou, Jiahua Liang, Longjun Liu*. “Explore a Novel Knowledge Distillation Framework for Network Learning and Low-Bit Quantization” [C], Chinese Automation Congress (CAC), 2021.

Lankun Li, Wancheng Liu, Ruiqi Lei, Longjun Liu*. “Design and Implementation of Infrared Image Preprocessing System basedon FPGA” [C], Chinese Automation Congress (CAC), 2021.

Haonan Zhang, Longjun Liu*, Hengyi Zhou, Wenxuan Hou, Hongbin Sun, Nanning Zheng. “AKECP: Adaptive Knowledge Extraction from Feature Maps for Fast and Efficient Channel Pruning”[C], 29th ACM International Conference on Multimedia (ACM MM), 2021. (CCF A类)

Haonan Zhang, Longjun Liu*, Hengyi Zhou, Hongbin Sun, Nanning Zheng. “CMD: Controllable Matrix Decomposition with Global Optimization for Deep Neural Network Compression”[J], Springer Journal Machine Learning (JML), 2021.

Wenxuan Hou, Longjun Liu,*, Jinxia Gao*, Anguo Zhu, Keyang Pan, Hongbin Sun, Nanning Zheng. “Exploring Effective DNN Models for Forensic Age Estimation based on Panoramic Radiograph Images”[C], International Joint Conference on Neural Networks (IJCNN), 2021

Wenxuan Hou, Longjun Liu*, Haonan Zhang, Hongbin Sun, Nanning Zheng. “DFSNet: Dividing-Fuse Deep Neural Networks with Searching Strategy for Distributed DNN Architecture”[J], ELSEVIER Journal Neurocomputing, 2021.

Xiaoqing Zhao, Longjun Liu*, Liang Si, Keyang Pan, Hongbin Sun, Nanning Zheng. “Adaptive Weight Mapping Strategy to Address the Parasitic Effects for ReRAM-based Neural Networks”[C], The IEEE International Conference on ASIC (ASICON), 2021.

Anguo Zhu, Longjun Liu*, Wenxuan Hou, Hongbin Sun, Nanning Zheng. “HSC: Leveraging Horizontal Shortcut Connections for Improving Accuracy and Computational Efficiency of Lightweight CNN”[J]， ELSEVIER Journal Neurocomputing, 2021

Baoting Li, Hang Wang; Xuchong Zhang; Jie Ren; Longjun Liu; Hongbin Sun; Nanning Zheng. "Dynamic Dataflow Scheduling and Computation Mapping Techniques for Efficient Depthwise Separable Convolution Acceleration," [J] IEEE Transactions on Circuits and Systems I: Regular Papers (TCAS-I), vol. 68, no. 8, Aug. 2021. (CCF A类)

Shaofei Yang#, Longjun Liu#, Yingxiang Li, Xinxin Li, Hongbin Sun and Nanning Zheng. "Lane Shared Bit-Pragmatic Deep Neural Network Computing Architecture and Circuit," [J]  in IEEE Transactions on Circuits and Systems II: Express Briefs (TCAS-II), vol. 68, no. 1, Jan. 2021.

Baoting Li, Longjun Liu*, Yanmin Jin, Peng Gao, Hongbin Sun and Nanning Zheng. "Designing Efficient Shortcut Architecture for Improving the Accuracy of Fully Quantized Neural Networks Accelerator,"[C] 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC), 2020, pp. 289-294.

Shaofei Yang, Longjun Liu*, Baoting Li, Hongbin Sun and Nanning Zheng. “Exploiting Variable Precision Computation Array for Scalable Neural Network Accelerators,”[C] IEEE International Conference on Artificial Intelligence Circuits and Systems （AICAS）, March 2020.

Yanming Jin, Longjun Liu*, Hongbing Sun, Nanning Zheng, “A Novel Strategy for Multi-Objective Tracking Framework based on Semi-online Mechanism”, [C] International Joint Conference on Neural Networks (IJCNN), 2020.