吕凯

博士、副教授

基本信息

办公电话：无	电子邮件： lvkai@bjtu.edu.cn
通讯地址：北京海淀区北京交通大学九教203	邮编：100044

研究兴趣

主要研究面向具身智能的图像视觉感知和智能机器控制，研究方向大类包含：计算机视觉 和 强化学习。

具体研究方向包括：

视频感知与理解 - 计算机视觉
具身智能 - 计算机视觉+强化学习
大模型后训练及其应用 - 强化学习

工作经历

(1) 2024年12月至今，北京交通大学计算机学院，副教授

(2) 2023年9月至2024年11月，北京交通大学计算机学院，讲师

(3) 2021年6月至2023年8月, 北京交通大学计算机学院, 师资博士后

教育背景

(1) 2014-09 至 2021-06, 北京航空航天大学, 软件工程, 硕博连读, 导师：李未院士、熊璋教授

(2) 2019-01 至 2020-01, 澳大利亚国立大学, 计算机科学与技术, 联合培养博士, 导师：Liang Zheng 博士

(3) 2018-06 至 2019-01, 新加坡科技设计大学, 计算机科学与技术, 联合培养博士, 导师：Liang Zheng 博士

论文/期刊

具身智能（计算机视觉+强化学习）：

[CVPR 2026] Jinwen Wang, Youfang Lin, Xiaobo Hu, Shuo Wang, Kai Lv. "Local Motion Matters: A Deconstruct–Recompose Paradigm for Reinforcement Learning Pre-training from Videos." The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026. (CCF A类会议)
[NN 2025] Xiaobo Hu, Youfang Lin, Jinwen Wang, Yue Liu, Shuo Wang, Hehe Fan, Kai Lv*. "Bidirectional Transition Consistency between Multi-Domain Observations for Visual Reinforcement Learning Generalization." Neural Networks, 2025. (SCI, CCF B类期刊, IF = 7.66)
[TOMM 2025] Xiaobo Hu, Youfang Lin, Jinwen Wang, Yue Liu, Shuo Wang, Hehe Fan, Kai Lv*. " Learning Robust Representations via BidirectionalTransition for Visual Reinforcement Learning." ACM Transactions on Multimedia Computing Communications and Applications, 2025. (SCI, Q2, CCF B类期刊, IF=5.1)
[ACM MM 2025] Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang, Sheng han, Shuo Wang, Kai Lv. "From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training." Proceedings of the 33rd ACM International Conference on Multimedia, 2025. (CCF A类会议)
[IJCAI 2024] Shuo Wang, Zhihao Wu, Xiaobo Hu, Jinwen Wang, Youfang Lin, Kai Lv*. "How to Learn Domain-Invariant Representations for Visual Reinforcement Learning: An Information-Theoretical Perspective." the 33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024. (CCF A类会议)
[AAAI 2024] Shuo Wang, Zhihao Wu, Xiaobo Hu, Jinwen Wang, Youfang Lin, Kai Lv*. "What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction." The 38th AAAI Conference on Artificial Intelligence (AAAI), 2024. (CCF A类会议)
[TOMM 2024] Xiaobo Hu, Youfang Lin, HeHe Fan, Shuo Wang, Zhihao Wu and Kai Lv*. "Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation" ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2024. (SCI, Q2, CCF B类期刊, IF=5.1)
[TCSVT 2023] Xiaobo Hu, Youfang Lin, Shuo Wang, Zhihao Wu and Kai Lv*. "Agent-Centric Relation Graph for Object Visual Navigation." IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023. (SCI, Q1, CCF B类期刊, IF=11.1, An 1区)
[TMM 2023] Shuo Wang, Zhihao Wu, Xiaobo Hu, Youfang Lin, Kai Lv*. "Skill-based Hierarchical Reinforcement Learning for Target Visual Navigation." IEEE Transactions on Multimedia (TMM), 20203. (SCI, CCF A类期刊, IF=9.7, An 1区)

大模型后训练及其应用（强化学习）：

[ICML 2026] Chang Yao, Youfang Lin, Shoucheng Song, Hao Wu, Yuqing Ma, Kai Lv*. "Role-Level Inductive Bias for Cross-Task Generalization in Multi-Agent Reinforcement Learning." The Forty-third International Conference on Machine Learning (ICML), 2026. (CCF A类会议)
[AAAI 2026] Hao Wu, Shoucheng Song, Chang Yao, Sheng Han, Huaiyu Wan, Youfang Lin, Kai Lv*. "Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution. " The 40th AAAI Conference on Artificial Intelligence (AAAI), 2026. (CCF A类会议)
[IJCAI 2025] Chang Yao, Youfang Lin, Shoucheng Song, Hao Wu, Yuqing Ma, Sheng Han, Kai Lv*. "From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination." The 34th International Joint Conference on Artificial Intelligence (IJCAI), 2025. (CCF A类会议)
[AAAI 2025] Shoucheng Song, Youfang Lin, Sheng han, Chang Yao, Hao Wu, Shuo Wang, Kai Lv*. "CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness." The 39th AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF A类会议)
[TSMC-S 2025] Hengrui Zhang, Youfang Lin, Shuo Shen, Sheng Han, Kai Lv*. "Off-policy Conservative Distributional Reinforcement Learning with Safety Constraints." IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC-S), 2025. (SCI, Q1, CCF B类期刊, IF=8.6)
[AAAI 2024] Hengrui Zhang, Youfang Lin, Shuo Shen, Sheng Han, Kai Lv*. "Enhancing Off-policy Constrained Reinforcement Learning through Adaptive Ensemble C Estimation." The 38th AAAI Conference on Artificial Intelligence (AAAI), 2024. (CCF A类会议)
Han Wang, Youfang Lin, Sheng Han and Kai Lv*. "Offline Reinforcement Learning with Diffusion-Based Behavior Cloning Term." The 16th International Conference on Knowledge Science, Engineering and Management (KSEM 2023). (CCF C类会议)
[TVT 2022] Hengrui Zhang, Youfang Lin, Sheng Han, and Kai Lv*. "Lexicographic Actor-Critic Deep Reinforcement Learning for Urban Autonomous Driving." IEEE Transactions on Vehicular Technology (TVT), 2022. (SCI, Q1, IF=6.239, An 2区)
Sheng Han, Youfang Lin, Zhihui Guo, and Kai Lv*. "A Lightweight and Style-Robust Neural Network for Autonomous Driving in End Side Devices." Connection Science (2022). (SCI, CCF C类期刊, IF=3.53)

视频感知与理解方向（计算机视觉）：

[TMM 2026] Huiqi Yang, Ying Shu, Hehe Fan, Youfang Lin, Kai Lv*. "Let Confidence Speak: Combining Small and Large Models via Pseudo Labeling for Unsupervised Domain Adaptation." IEEE Transactions on Multimedia (TMM), 2026. (SCI, CCF A类期刊, IF=9.7, An 1区)
[AAAI 2025] Kai Lv, Yunlong Li, Zhuo Chen, Shuo Wang, Sheng Han, Youfang Lin*. "Infer the Whole from a Glimpse of a Part: Keypoint-based Knowledge Graph for Vehicle Re-identification." The 39th AAAI Conference on Artificial Intelligence (AAAI), 2025. (CCF A类会议)
[TOMM 2024] Kai Lv, Haobo Chen, Chuyang Zhao, Kai Tu, Junru Chen, Yadong Li, Boxun Li, and Youfang Lin*. "Style Variable and Irrelevant Learning for Generalizable Person Re-identification." ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2024. (SCI, Q2, CCF B类期刊, IF=5.1)
[TITS 2023] Kai Lv, Shuo Wang, Shuai Han, Youfang Lin*. "Spatially-Regularized Features for Vehicle Re-identification: An Explanation of Where Deep Models Should Focus." IEEE Transactions on Intelligent Transportation Systems (TITS), 2023. (SCI, Q1, CCF B类期刊, IF=8.5)
[IJCAI workshop 2023] Kai Lv, Shuai Han and Youfang Lin. "Generalization between Different Viewpoints with A Feature Selection Method for Vehicle Re-identification." 32nd International Joint Conference on Artificial Intelligence (IJCAI) Workshop 2023.
[TIP 2020] Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, and Liang Zheng. "Pose-Based View Synthesis for Vehicles: A Perspective Aware Method." IEEE Transactions on Image Processing (TIP), 2020: 5163-74. （SCI, CCF A类期刊, IF=13.7, An 1区）
[TMM 2020] Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, and Liang Zheng. "Improving Driver Gaze Prediction with Reinforced Attention." IEEE Transactions on Multimedia (TMM), 2020: 4198-207. (SCI, CCF A类期刊, IF=9.7, An 1区)
[JIOT 2020] Hao Sheng, Kai Lv*, Yang Liu, Wei Ke, Weifeng Lyu, Zhang Xiong, and Wei Li. "Combining Pose Invariant and Discriminative Features for Vehicle Reidentification." IEEE Internet of Things Journal 8, no. 5 (2020): 3189-200. (SCI, IF=9.471, An 1区)
[CVPR Challenge 第三名] Kai Lv, Heming Du, Yunzhong Hou, Weijian Deng, Hao Sheng, Jianbin Jiao, and Liang Zheng. "Vehicle Re-Identification with Location and Time Stamps." CVPR Workshops, 2019.

科研项目

国家自然科学基金"面上": 面向动态交互环境的感控虚实迁移技术研究, 2026-2029，主持

自然科学类人才基金项目: 面向集群协同的多智能体强化学习算法研究, 2024-2026，主持

国家级"四总部": 基于多智能体强化学习的编队协同空战决策算法研究, 2024-2025，主持

国家自然科学基金"青年基金": 面向多视角车辆重识别的多维一致性学习方法研究, 2023-2025，主持

招生专业

计算机科学与技术博士
人工智能博士
计算机技术博士
计算机科学与技术硕士
计算机技术硕士
人工智能硕士
软件工程硕士
大数据技术与工程硕士
新一代电子信息技术（含量子技术等）硕士
低空技术与工程硕士

教学工作

本科生课程：《操作系统》秋季-64课时

硕士研究生课程：《深度学习》暑期-32课时

博士研究生课程：《强化学习前沿理论与技术》秋季-32课时

社会兼职

担任知名国际会议领域主席，包括：

ACM Multimedia (ACM MM)
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Advanced Video and Signal Based Surveillance (AVSS)

担任知名国际会议和期刊的审稿人，包括：

International Conference on Machine Learning (ICML)
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IEEE Trans on MultiMedia (TMM)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)等。

吕凯