个人简历
基本信息
刘德彬，男，1997年生，2024年6月份于华中科技大学取得计算机系统结构专业工学博士学位，中共党员，副研究员，硕士生导师，中原青年拔尖人才，CCF协同计算专业委员会委员，工业物联网技术与应用专委会委员。2024年8月入职郑州大学计算机与人工智能学院，主要研究方向有多模态学习、深度神经网络模型优化、3D点云生成、3D姿态迁移、神经网络模型压缩与加速、大模型高效推理等；在IEEE TPAMI、TIP、TPDS、TC、TMC、TIFS、TCAD、TITS、TII、ACM TOMM、IEEE Communications Surveys and Tutorials、CVPR、NeurIPS、ICME等期刊会议发表论文40余篇，获ICME（CCF B）最佳论文提名；担任AAAI 2026/ACM MM 2026程序委员会委员，担任国际顶级期刊/会议ACM MM，NeurlPS、AAAI、ICLR、CVPR、ICML、IEEE TIFS、TITS、TDSC、TMC、TNNLS、TII、TVT、TSUSC、计算机学报等审稿人。最新动态：https://jayliudebin.github.io/。
学术论文
[1]Debin Liu, Xiang Bai, Ruonan Zhao, Xianjun Deng, and Laurence T. Yang. Dual-grained Lightweight Strategy. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024, 46(12): 10228-10245. (IF: 20.4, 中科院一区Top, CCF A)
[2]Debin Liu, Xiang Bai, Ruonan Zhao, Xianjun Deng, Shibo He and Laurence T. Yang. A Simple but Efficient Method to Achieve High Performance with Extreme Sparsity. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026. (Accepted, IF: 20.4, 中科院一区Top, CCF A)
[3]BoCheng Ren, Yuanyuan Yi, Jun Feng, Qingchen Zhang and Debin Liu*. Prototype Matters: Domain-Wise Prototype Induction for Zero-Shot Recognition IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), doi: 10.1109/TPAMI.2026.3742105, 2026. ( IF: 20.4, 中科院一区Top, CCF A)
[4]Shijie Lv, Debin Liu*, Laurence T. Yang, Xiaosong Peng, Ruonan Zhao, Zecan Yang, and Jun Feng. Based on Tensor Core Sparse Kernels Accelerating Deep Neural Networks. IEEE Transactions on Parallel and Distributed Systems (TPDS), 2026, 37(2): 353-364. (IF: 5.9, 中科院二区, CCF A)
[5]Ruonan Zhao, Zheng Wang, Debin Liu*, Shijie Lv, and Laurence T. Yang. FedARA: Resource-adaptive Low-rank Personalized Federated Learning via Anchor-driven Representation Alignment on Heterogeneous Edge Devices. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (CCF A会议)
[6]Tianzhe Xiao, Haozhao Wang, Yichen Li, Qiyu Qin, Debin Liu* and Ruixuan Li. FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning. The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026. (CCF A会议)
[7]Bin Luo, Laurence T. Yang, Debin Liu* and Audrey Yang. The Scalable Tensor-based Codebook Product Quantization for Multi-Label Image Retrieval. IEEE Transactions on Image Processing (TIP), 2026. (Accepted, IF: 15.3, 中科院一区Top, CCF A)
[8]Shijie Lv, Ruonan Zhao, Debin Liu*, Laurence T. Yang, and Jinhua Cui. QaQuant: Towards Efficient INT4 Quantization for High-Performance LLMs Services Deployment on Edge Devices. IEEE Transactions on Computers (TC), 2026. (大修, IF: 4.9, 中科院二区, CCF A)
[9]Ruonan Zhao, Zheng Wang, Debin Liu*, Xianjun Deng, Wei Liu, Zhiyuan Ma and Laurence T. Yang. TPFed: When Tensor-Train Decomposition Meets Hybrid Knowledge Prototype for Resource-Adaptive Personalized Federated Learning. IEEE Transactions on Mobile Computing (TMC), 2026. (大修, IF: 8.2, 中科院一区, CCF A)
[10]Zecan Yang, Laurence T. Yang, Huaimin Wang, Honglu Zhao, and Debin Liu. Bayesian Nonnegative Tensor Completion with Automatic Rank Determination. IEEE Transactions on Image Processing (TIP), vol. 34, pp. 2036-2051, 2025. (IF: 15.3, 中科院一区Top, CCF A)
[11]Jun Feng, Xuchi Cheng, Hong Sun, Shunli Zhang, and Debin Liu. Panther: Pracical Secure 2-Party Neural Network Inference. IEEE Transactions on Information Forensics and Security (TIFS), vol. 20, pp. 1149-1162. 2025. (IF: 8.7; 中科院一区Top；CCF A)
[12]Bocheng Ren, Yuanyuan Yi, Qingchen Zhang, and Debin Liu. Zero-Shot Image Recognition via Learning Dual Prototype Accordance Across Meta-Domains. IEEE Transactions on Image Processing (TIP), vol. 34, pp. 6361-6373, 2025. (IF: 15.3, 中科院一区Top, CCF A)
[13]Shuilong Wang, Laurence T Yang, Debin Liu, Ruonan Zhao, Xianjun Deng, Cannian Zou, and Xiaoxuan Fan. Improving Ethereum Mixing Address Linking with Tensor Computation, Neighbor Data Utilization and Asymmetric Information Modeling. IEEE Transactions on Information Forensics and Security (TIFS), vol. 20, pp. 8658-8671. 2025. (IF: 8.7; 中科院一区Top；CCF A)
[14]Xiaosong Peng, Laurence T Yang, Xiaokang Wang, Debin Liu, and Jie Li. A High-Efficiency Parallel Mechanism for Canonical Polyadic Decomposition on Heterogeneous Computing Platform. IEEE Transactions on Computers (TC), vol. 74, no. 10, pp. 3377-3389, 2025. (IF: 4.9, 中科院二区, CCF A)
[15]Kai Tang, Jinhua Cui, Changhao Wen, Shiqiang Nie, Debin Liu, Yaliang Zhao, and Laurence T Yang. WOM-FTL: An Efficient FTL for High-Density Flash Memory Through WOM-v Codes. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), doi: 10.1109/TCAD.2025.3571833. (IF: 3.6, 中科院三区, CCF A)
[16]Yuankai Zhang, Wei Liu, Jun Wang, HaoZhao Wang, Debin Liu, Rui Zhang, Zhigang Zeng, Laurence T. Yang and Ruixuan Li. Asymmetric Learning Rates for Robust Cooperative Rationalization: A Flexible Lipschitz Restraint. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026 (大修, IF: 20.4, 中科院一区Top, CCF A)
[17]Debin Liu, Laurence T. Yang, Ruonan Zhao, Jiawei Wang, and Xia Xie. Lightweight Tensor Deep Computation Model with Its Application in Intelligent Transportation Systems. IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 23, no. 3, pp. 2678-2687, 2022. (IF: 9.1, 中科院一区Top, CCF B)
[18]Debin Liu, Laurence T. Yang, Ruonan Zhao, Xianjun Deng, Chenlu Zhu, and Yiheng Ruan. Multi-tree Compact Hierarchical Tensor Recurrent Neural Networks for Intelligent Transportation Systems Edge Devices. IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 24, no. 8, pp. 8719-8729, 2024. (IF:9.1, 中科院一区Top, CCF B)
[19]Jinglin Zhao, Debin Liu*, Laurence T. Yang, Ruonan Zhao, Zheng Wang, and Zhe Li. TD3D: Tensor-based Discrete Diffusion Process for 3D Shape Generation. IEEE International Conference on Multimedia and Expo (ICME), 2024. (CCF B, 最佳论文提名)
[20]Ruonan Zhao, Laurence T. Yang, Debin Liu*, and Wanli Lu. Tensor-empowered Communication-efficient and Trustworthy Federated Learning for Heterogeneous Intelligent Space-Air-Ground Integrated IoT. IEEE Internet of Things Journal (IOT), vol. 10, no. 23, pp. 20285-20296, 2023. (IF: 8.7, 中科院一区Top)
[21]Ruonan Zhao, Laurence T. Yang, Debin Liu*, Xianjun Deng, Xueming Tang, and Sahil Garg. Tensor-based Secure Truthful Incentive Mechanism for Mobile Crowdsourcing in IoT-enabled Maritime Transportation Systems. IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 25, no. 5, pp. 3341-3351, 2024. (IF: 9.1, 中科院一区Top, CCF B)
[22]Ruonan Zhao, Laurence T. Yang, Debin Liu*, Wanli Lu, and Xiangli Yang. Lightweight Tensor-based GRU for Trustworthy and Communication Efficient Federated Learning in Industrial IoT. IEEE Transactions on Industrial Informatics (TII), vol. 21, no. 3, pp. 2043-2052, 2025. (IF: 9.8, 中科院一区Top)
[23]Debin Liu, Laurence T. Yang, Puming Wang, Ruonan Zhao, and Qingchen Zhang. TT-TSVD: A Multi-modal Tensor Train Decomposition with Its Application in Convolutional Neural Networks for Smart Healthcare. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. 18, no. 41, pp. 1-17, 2022. (IF: 5.6, 中科院三区, CCF B)
[24]Debin Liu, Laurence T. Yang, Ruonan Zhao, Jinhua Cui, and Xiangli Yang. An Efficient Tensor-based Transformer for Industrial Internet of Things. IEEE Transactions on Network Science and Engineering (TNSE), vol. 11, no. 3, pp. 2574-2585, 2024. (IF: 7.3, 中科院二区)
[25]Debin Liu, Laurence T. Yang, Ruonan Zhao, and Honglu Zhao. Tensor-empowered Hardware-friendly Lightweight Deep Neural Networks. IEEE Transactions on Consumer Electronics (TCE), vol. 71, no. 1, pp. 2175-2185, 2025. (IF: 9.9, 中科院二区)
[26]Haixv Lu, Debin Liu*, Laurence T Yang, Ruonan Zhao, Shijie Lian, Songhe Yuan, and Junjie Su. A Zero-shot High-dimensional Feature Fusion with STF-GAN for Cross-domain Image Reconstruction. IEEE Journal of Selected Topics in Signal Processing (JSTSP), 2025, doi: 10.1109/JSTSP.2025.3600191. (IF: 8.5, 中科院一区Top)
[27]Haixv Lu, Debin Liu*, Laurence T Yang, Ruonan Zhao, Shijie Lv, Jiawei Wang, and Xiaosong Peng. Share Token Tensorized Attention Fusion: Enhancing Audio-Visual Emotion Recognition for Consumer Electronics. IEEE Transactions on Consumer Electronics (TCE), 2025, doi: 10.1109/TCE.2025.3599517. (IF: 9.9, 中科院二区)
[28]Ruonan Zhao, Laurence T. Yang, Debin Liu*, Xiangli Yang, and Meiqi Wang. Tensor-empowered Lightweight Representations for Personalized Federated Learning in Heterogeneous 6G Networks. IEEE Network, vol. 39, no. 2, pp. 115-123, 2025. (IF: 8.8, 中科院三区)
[29]Ruonan Zhao, Laurence T. Yang, Debin Liu, Xianjun Deng, and Yijun Mo. A Tensor-based Truthful Incentive Mechanism for Blockchain-enabled Space-Air-Ground Integrated Vehicular Crowdsensing. IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 23, no. 3, pp. 2853-2862, 2022. (IF: 9.1, 中科院一区Top, CCF B)
[30]Ruonan Zhao, Laurence T. Yang, Debin Liu, Wanli Lu, Chenlu Zhu, and Yiheng Ruan. Tensor-empowered LSTM for Communication-efficient and Privacy-enhancd Cognitive Federated Learning in Intelligent Transportation Systems. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. 20, no. 33, pp. 1-21, 2023. (IF: 5.6, 中科院三区, CCF B)
[31]Ruonan Zhao, Laurence T. Yang, Debin Liu, Xiaokang Zhou, Xianjun Deng, and Xueming Tang. A Multi-modal Tensor Ring Decomposition for Communication-efficient and Trustworthy Federated Learning for Its Covid-19 Scenario. IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 25, no. 5, pp. 3535-3547, 2024. (IF: 9.1; 中科院一区Top; CCF B)
[32]Laurence T. Yang, Ruonan Zhao, Debin Liu, Wanli Lu, and Xianjun Deng. Tensor Empowered Federated Learning for Cyber-Physical-Social Computing and Communication Systems. IEEE Communications Surveys and Tutorials, vol. 25, no. 3, pp. 1909-1940, 2023. (IF: 50.6; 中科院一区Top)
[33]Honglu Zhao, Laurence T. Yang, Zecan Yang, Debin Liu, Xin Nie, and Bocheng Ren. Sparse Bayesian Tensor Completion for Data Recovery in Intelligent IoT Systems. IEEE Internet of Things Journal (IOT), vol. 11, no. 15, pp. 25682-25693, 2024. (IF: 8.7, 中科院一区Top)
[34]Songhe Yuan, Laurence T Yang, Debin Liu, Xiaokang Wang, and Jieming Yang. THPFF: A tensor-based high-precision feature fusion model for multi-source data in smart healthcare systems. Information Fusion, vol. 124, pp.103324. 2025. (IF: 17.4, 中科院一区Top)
[35]Xueru Bai, Jieyuan Chen, Laurence T. Yang, Debin Liu, Cen Chen, Xiaokang Wang, and M. Jamal Deen. TT-RNNPool3D: A Tensor-based High-order RNNPool Model for Mobile Edge Consumer Applications. IEEE Transactions on Consumer Electronics (TCE), 2025, doi: 10.1109/TCE.2024.3435410. (IF: 9.9, 中科院二区)
[36]Shijie Lian, Ziyi Zhang, Hua Li, Laurence T. Yang, Mengyu Ren, Debin Liu and Wenhui Wu. TUGS: Physics-based Compact Representation of Underwater Scenes by Tensorized Gaussians. IEEE International Conference on Multimedia and Expo (ICME), 2026. (CCF B, Oral)
科研项目经历
[1]国家自然科学基金青年基金项目，30万元，项目负责人
[2]中国博士后科学基金面上项目，16万元（配套8万元），项目负责人
[3]曙光信息产业（北京）有限公司开放课题项目，20万元，项目负责人
[4]中国联合网络通信有限公司河南省分公司横向项目，80万元，课题负责人
[5]河南省“中原英才计划”—中原青年拔尖人才项目，50万元，项目负责人
[6]国家自然科学基金重点项目-安全关键汽车信息物理系统建模理论与系统设计(2020.01-2024.12)，课题骨干，参与
[7]华中科技大学人工智能与智能交通联合技术中心与湖北楚天智能交通有限公司合作项目-智慧交通运营监测指挥调度系统 (2021.04-2024.12)，项目骨干，参与
[8]科技创新2030“新一代人工智能（2030）”重大项目-人工智能基础模型关键技术研究 (2023.03-2024.03)，项目骨干，参与
[9]国家重点研发项目-基于时隙映射的细粒度三层软切片及基于New IP的确定性转发技术 (2020.11-2023.10)，课题骨干，参与
获奖情况
[1]2026年ACM China新星奖（郑州分会，共3位，并唯一推荐到国家评选）
[2]2026年UK National Edge AI Hub 未来之星奖（全球3个）
[3]2025年 IEEE Cybermatics Congress (ICA3PP(CCF C类会议)/Blockchain/SmartData/CPSCom/iThings/GreenCom), 郑州, 河南, IEEE Excellent Organization Organization Award-Local Chiar
[4]2024年 IEEE Technical Committee on Scalable Computing 杰出博士论文奖 （全球5个）
[5]2024年 IEEE AI+ Congress (TrustCom (CCF C类会议)/BigDataSE/CSE/EUC/iSCI), 三亚, 海南, IEEE Excellent Organization Award-Organizing Committee Chair
[6]2024年 IEEE AI for Science Congress (ISPA (CCF C类会议)/BDCloud/SocialCom/SustainCom/SpaCCS), 开封, 河南, IEEE Outstanding Service Award-Organizing Committee Member
[7]2023年 IEEE Cybermatics Congress(Blockchain/SmartData/CPSCom/IThings/CBD/ICPADS (CCF C类会议)), 海花岛, 海南, IEEE Distinguished Services Award-Local Chair
[8]2023年 华中科技大学“达梦奖学金”
[9]2022年 National CyberSecurity Center International Congress (IEEE TrustCom (CCF C类会议)/BigDataSE/CSE/EUC/iSCI), 武汉, 湖北, IEEE Outstanding Leadership Award-Publicity Chair
[10]2021年 IEEE Hyper-Intelligence Congress (HPCC (CCF C类会议)/Smartcity/DSS/DependSys/GPC/DIKW), 海口, 海南, IEEE Outstanding Leadership Award-Publicity Chair
[11]2018年 全国大学生电子设计竞赛全国二等奖
[12]2017年 本科生“国家奖学金”
发明专利
[1]阮一恒; 刘德彬; 朱晨露; 杨天若; 邓贤君，一种基于张量的混合推荐方法及系统，已授权
[2]姚博文; 杨天若; 欧阳泽宇; 徐泽汐; 刘德彬; 赵若男; 伦嘉铭; 丁光宇; 易永亮; 严运广; 张卫国; 张鹏飞，基于张量超图注意力网络的半监督节点分类方法及系统，已受理
[3]杨天若; 谭子熠; 杨驰; 崔金华; 刘德彬; 赵若男; 邓贤君，跨域驾驶异常行为检测模型建立方法及其应用，已授权
[4]郭赛迪; 杨天若; 吕秋杰; 赵若男; 刘德彬，一种基于时空因果的跨模态心脏图像分割方法及系统，已受理
[5]吕秋杰; 杨天若; 郭赛迪; 赵若男; 刘德彬，一种基于跨域元学习的药物分子属性预测方法及系统，已受理
[6]杨天若; 谭子熠; 杨驰; 崔金华; 刘德彬; 赵若男; 邓贤君，一种车辆行为识别模型的构建方法及应用，已受理
[7]杨天若; 赵景林; 刘德彬; 崔金华; 赵若男; 王正; 邓贤君，3D形状还原方法及还原模型的构建方法、设备、存储介质，已受理
[8]杨天若; 路万里; 赵若男; 刘德彬; 崔金华; 邓贤君，基于张量计算和同态门限的安全联邦学习方法及系统，已受理
[9]杨天若; 路万里; 赵若男; 刘德彬; 崔金华; 邓贤君，一种基于多密钥同态加密的联邦学习方法和系统，已受理
[10]朱晨露; 刘德彬; 阮一恒; 张立杰; 邓贤君; 杨天若，一种基于张量的高效Transformer的架构方法，已受理
成果落地
[1]面向工业视觉模型设计与轻量化部署。将本人独立设计与研发的一种多目标检测轻量化模型部署到边缘盒子（RK3588和NVIDIA Orin NX芯片），实现32路摄像头多目标多功能实时检测（功能包括：抽烟检测、玩手机检测、明火检测、烟雾检测、电池焚烧检测、口罩人脸识别、反光衣检测、安全帽检测、黑白名单区域入侵检测、在岗检测、人员密集度检测、水下鱼类姿态检测、水下鱼群种类检测等），并已经落地应用，在无锡市工地、南通市工厂、苏州市园区和南非工地进行实际部署与应用，并产生了600万元的经济效益。
[2]小维机器人。本人独立研发的一种人体姿势估计（可判定站立、摔倒、坐等行为）、视觉心率检测（心率和血氧）、多目标追踪和行人重识别模型（可自主跟随设定目标人物，实时看护目标人物）在小维机器人（RK3588芯片）上进行实际部署应用，已落地江南大学附属医院。
[3]面向智能监考系统的模型设计与轻量化部署。本人独立研发的智能监考系统（功能包括：考生携带可疑物品检测、考生提前作答检测、考生站立检测、考生举手检测、考生销毁试卷/答题卡检测、考生考试结束后长时间不离场检测、考生群体举手检测、考生群体站立检测、考生群体考后继续作答检测、考生人数统计、监考员提前发卷检测、监考员少于两人检测、监考员未按时到达考场检测、监考员未展示试卷袋/答题卡袋检测、监考员手持可疑物品检测、监考员抽烟检测、监考员在考生位置就坐检测等）目前已形成初步产品，与河南联通合作，正在进一步优化。
[4]BossAI。本人与杭州PeekVision公司合作，设计了一款纯国产的智能体桌面电脑，其芯片、系统和模型等都是国产，在桌面设备层面实现企业级AI能力，实现“高算力、低功耗、即插即用”，目前已落地应用，并产生了百万级的经济效益。
招生信息
欢迎对人工智能、计算机视觉、神经网络模型优化、多模态学习、大模型高效推理等方向感兴趣的同学加入，有意向的同学可以将本人简历发送至：debinliuhust@gmail.com，联系电话: 18569968326，微信：bb1104111625。
招生加分项：1）同学能够在短暂的学术研究里坚定自我选择、努力拔尖、坐的住冷板凳，方能出得了了不起的研究成果；2）具备较好的英语能力、数学基础和人工智能相关的基础；3）具备较好的行动力，能够及时行动，而不是一直处于想法阶段；4）具备较好的编程能力（如python等），熟悉深度学习框架（PyTorch、TensorFlow）；5）本科具有科研经历，竞赛经历。
后话：希望加入团队的学生，我们能够一起在科研中探索，彼此相互学习与成长，朝着自己原本的目的地逐步前进！
