Kai Lv

About Me

Kai Lv 吕凯

I am an Associate Professor with the School of Computer Science and Technology at Beijing Jiaotong University. My research focuses on learning-based intelligent systems, especially embodied intelligent manipulation, multi-agent collaboration, and re-identification.

My current work studies how agents understand dynamic scenes, coordinate with other agents, and make reliable decisions from visual observations. I am also interested in practical learning systems that connect perception, reasoning, and action.

Research map covering embodied intelligence, multi-agent learning, and re-identification
3 Core research themes
2026 Latest listed publications
BJTU School of Computer Science and Technology
  1. One paper on role-level inductive bias for multi-agent reinforcement learning was accepted by ICML 2026.
  2. One paper on unsupervised domain adaptation was accepted by IEEE Transactions on Multimedia.
  3. One paper on reinforcement learning pre-training from videos was accepted by CVPR 2026.
  4. One paper on active inference for decentralized execution was accepted by AAAI 2026.
  5. One paper on visual reinforcement learning generalization was accepted by Neural Networks.
  6. One paper on robust representations for visual reinforcement learning was accepted by ACM Transactions on Multimedia Computing, Communications, and Applications.
  7. One paper on reinforcement learning pre-training was accepted by ACM Multimedia 2025.
  8. One paper on continual multi-agent coordination was accepted by IJCAI 2025.
  9. One paper on offline safe reinforcement learning was accepted by AAMAS 2025.
  10. Two papers were accepted by AAAI 2025, covering vehicle re-identification and communication delay-tolerant multi-agent collaboration.
  11. One paper on safe reinforcement learning was accepted by IEEE Transactions on Systems, Man, and Cybernetics: Systems.

Working Experience

Dec 2024 - Present

Associate Professor

School of Computer Science and Technology, Beijing Jiaotong University

Sep 2023 - Nov 2024

Lecturer

School of Computer Science and Technology, Beijing Jiaotong University

Jun 2021 - Aug 2023

Faculty Postdoctoral Researcher

Beijing Jiaotong University

Selected Publications

中文论文页

Embodied Intelligent Manipulation

Visual RL
CVPR 2026
CVPR 2026

Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos

Jinwen Wang, Youfang Lin, Xiaobo Hu, Shuo Wang, Kai Lv

The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026.

NN 2025
NN 2025

Bidirectional Transition Consistency between Multi-Domain Observations for Visual Reinforcement Learning Generalization

Xiaobo Hu, Youfang Lin, Jinwen Wang, Yue Liu, Shuo Wang, Hehe Fan, Kai Lv*

Neural Networks, 2025.

TOMM 2025
TOMM 2025

Learning Robust Representations via Bidirectional Transition for Visual Reinforcement Learning

Xiaobo Hu, Youfang Lin, Jinwen Wang, Yue Liu, Shuo Wang, Hehe Fan, Kai Lv*

ACM Transactions on Multimedia Computing, Communications and Applications, 2025.

ACM MM 2025
ACM MM 2025

From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training

Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang, Sheng Han, Shuo Wang, Kai Lv

Proceedings of the 33rd ACM International Conference on Multimedia, 2025.

IJCAI 2024
IJCAI 2024

How to Learn Domain-Invariant Representations for Visual Reinforcement Learning: An Information-Theoretical Perspective

Shuo Wang, Zhihao Wu, Xiaobo Hu, Jinwen Wang, Youfang Lin, Kai Lv*

The 33rd International Joint Conference on Artificial Intelligence, 2024.

AAAI 2024
AAAI 2024

What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction

Shuo Wang, Zhihao Wu, Xiaobo Hu, Jinwen Wang, Youfang Lin, Kai Lv*

The 38th AAAI Conference on Artificial Intelligence, 2024.

TOMM 2024
TOMM 2024

Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation

Xiaobo Hu, Youfang Lin, Hehe Fan, Shuo Wang, Zhihao Wu, Kai Lv*

ACM Transactions on Multimedia Computing, Communications and Applications, 2024.

TCSVT 2023
TCSVT 2023

Agent-Centric Relation Graph for Object Visual Navigation

Xiaobo Hu, Youfang Lin, Shuo Wang, Zhihao Wu, Kai Lv*

IEEE Transactions on Circuits and Systems for Video Technology, 2023.

TMM 2023
TMM 2023

Skill-based Hierarchical Reinforcement Learning for Target Visual Navigation

Shuo Wang, Zhihao Wu, Xiaobo Hu, Youfang Lin, Kai Lv*

IEEE Transactions on Multimedia, 2023.

Multi-Agent Collaboration

MARL
ICML 2026
ICML 2026

Role-Level Inductive Bias for Cross-Task Generalization in Multi-Agent Reinforcement Learning

Chang Yao, Youfang Lin, Shoucheng Song, Hao Wu, Yuqing Ma, Kai Lv*

The Forty-third International Conference on Machine Learning, 2026.

AAAI 2026
AAAI 2026

Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution

Hao Wu, Shoucheng Song, Chang Yao, Sheng Han, Huaiyu Wan, Youfang Lin, Kai Lv*

The 40th AAAI Conference on Artificial Intelligence, 2026.

IJCAI 2025
IJCAI 2025

From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination

Chang Yao, Youfang Lin, Shoucheng Song, Hao Wu, Yuqing Ma, Sheng Han, Kai Lv*

The 34th International Joint Conference on Artificial Intelligence, 2025.

AAAI 2025
AAAI 2025

CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness

Shoucheng Song, Youfang Lin, Sheng Han, Chang Yao, Hao Wu, Shuo Wang, Kai Lv*

The 39th AAAI Conference on Artificial Intelligence, 2025.

TSMC-S 2025
TSMC-S 2025

Off-policy Conservative Distributional Reinforcement Learning with Safety Constraints

Hengrui Zhang, Youfang Lin, Shuo Shen, Sheng Han, Kai Lv*

IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2025.

AAAI 2024
AAAI 2024

Enhancing Off-policy Constrained Reinforcement Learning through Adaptive Ensemble C Estimation

Hengrui Zhang, Youfang Lin, Shuo Shen, Sheng Han, Kai Lv*

The 38th AAAI Conference on Artificial Intelligence, 2024.

KSEM 2023
KSEM 2023

Offline Reinforcement Learning with Diffusion-Based Behavior Cloning Term

Han Wang, Youfang Lin, Sheng Han, Kai Lv*

The 16th International Conference on Knowledge Science, Engineering and Management, 2023.

TVT 2022
TVT 2022

Lexicographic Actor-Critic Deep Reinforcement Learning for Urban Autonomous Driving

Hengrui Zhang, Youfang Lin, Sheng Han, Kai Lv*

IEEE Transactions on Vehicular Technology, 2022.

Connection Science 2022
Connection Science 2022

A Lightweight and Style-Robust Neural Network for Autonomous Driving in End Side Devices

Sheng Han, Youfang Lin, Zhihui Guo, Kai Lv*

Connection Science, 2022.

Object Re-Identification

Re-ID
TMM 2026
TMM 2026

Let Confidence Speak: Combining Small and Large Models via Pseudo Labeling for Unsupervised Domain Adaptation

Huiqi Yang, Ying Shu, Hehe Fan, Youfang Lin, Kai Lv*

IEEE Transactions on Multimedia, 2026.

AAAI 2025
AAAI 2025

Infer the Whole from a Glimpse of a Part: Keypoint-based Knowledge Graph for Vehicle Re-identification

Kai Lv, Yunlong Li, Zhuo Chen, Shuo Wang, Sheng Han, Youfang Lin*

The 39th AAAI Conference on Artificial Intelligence, 2025.

TOMM 2024
TOMM 2024

Style Variable and Irrelevant Learning for Generalizable Person Re-identification

Kai Lv, Haobo Chen, Chuyang Zhao, Kai Tu, Junru Chen, Yadong Li, Boxun Li, Youfang Lin*

ACM Transactions on Multimedia Computing, Communications and Applications, 2024.

TITS 2023
TITS 2023

Spatially-Regularized Features for Vehicle Re-identification: An Explanation of Where Deep Models Should Focus

Kai Lv, Shuo Wang, Shuai Han, Youfang Lin*

IEEE Transactions on Intelligent Transportation Systems, 2023.

IJCAI Workshop 2023
IJCAI Workshop 2023

Generalization between Different Viewpoints with A Feature Selection Method for Vehicle Re-identification

Kai Lv, Shuai Han, Youfang Lin

32nd International Joint Conference on Artificial Intelligence Workshop, 2023.

TIP 2020
TIP 2020

Pose-Based View Synthesis for Vehicles: A Perspective Aware Method

Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, Liang Zheng

IEEE Transactions on Image Processing, 2020.

TMM 2020
TMM 2020

Improving Driver Gaze Prediction with Reinforced Attention

Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, Liang Zheng

IEEE Transactions on Multimedia, 2020.

JIOT 2020
JIOT 2020

Combining Pose Invariant and Discriminative Features for Vehicle Reidentification

Hao Sheng, Kai Lv*, Yang Liu, Wei Ke, Weifeng Lyu, Zhang Xiong, Wei Li

IEEE Internet of Things Journal, 2020.

CVPR Workshops 2019
CVPR Workshops 2019

Vehicle Re-Identification with Location and Time Stamps

Kai Lv, Heming Du, Yunzhong Hou, Weijian Deng, Hao Sheng, Jianbin Jiao, Liang Zheng

CVPR Workshops, 2019.

* denotes corresponding author.