| Iso-dream: Isolating and leveraging noncontrollable visual dynamics in world models M Pan, X Zhu, Y Wang, X Yang Advances in neural information processing systems 35, 23178-23191, 2022 | 84 | 2022 |
| URRNet: A unified relational reasoning network for vehicle re-identification J Qian, M Pan, W Tong, R Law, EQ Wu IEEE Transactions on Vehicular Technology 72 (9), 11156-11168, 2023 | 36 | 2023 |
| Model-based reinforcement learning with isolated imaginations M Pan, X Zhu, Y Zheng, Y Wang, X Yang IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (5), 2788-2803, 2023 | 16 | 2023 |
| MRNet: A keypoint guided multi-scale reasoning network for vehicle re-identification M Pan, X Zhu, Y Li, J Qian, P Liu International Conference on Neural Information Processing, 469-478, 2020 | 7 | 2020 |
| Continual visual reinforcement learning with a life-long world model M Pan, W Zhang, G Chen, X Zhu, S Gao, Y Wang, X Yang Joint European Conference on Machine Learning and Knowledge Discovery in …, 2025 | 6 | 2025 |
| Video-enhanced offline reinforcement learning: A model-based approach M Pan, Y Zheng, J Li, Y Wang, X Yang arXiv preprint arXiv:2505.06482, 2025 | 4 | 2025 |
| Model-based reinforcement learning with multi-task offline pretraining M Pan, Y Zheng, Y Wang, X Yang Joint European Conference on Machine Learning and Knowledge Discovery in …, 2024 | 2 | 2024 |
| MetaTrader: Learning to Generalize RL Trading Policies Beyond Offline Data H Yuan, M Pan, Y Wang, S Gao, X Yang Proceedings of the AAAI Conference on Artificial Intelligence 40 (33), 28023 …, 2026 | 1 | 2026 |
| Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization H Yuan, M Pan, Y Wang, S Gao, PS Yu, X Yang arXiv preprint arXiv:2505.12759, 2025 | 1 | 2025 |
| LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory J Cao, Z Zhao, B Feng, Z Hu, R Li, H Wan, C Li, J Li, W Cai, L Bai, ... arXiv preprint arXiv:2605.02288, 2026 | | 2026 |
| FOCUS: High-Dimensional Model-Based RL via Focused Control Unit Sampling Y Zheng, M Pan, J Li, Y Wang, X Yang | | |
Yunbo WangAssociate Professor, Shanghai Jiao Tong UniversityVerified email at sjtu.edu.cn
