刘梦源 研究员
研究方向：具身智能、机器人感知与操作、人体运动分析
教育背景：
| 2012-2017 | 北京大学 | 信息科学技术学院 博士 | |
| 2017-2018 | 新加坡南洋理工大学 | 电子电气工程学院 博士后 | |
| 2018-2020 | 腾讯科技有限公司 | 人工智能领域 高级研究员 | |
| 2020-2023 | 中山大学 | 长聘副教授、“百人计划”人才 | |
| 2023-至今 | 北京大学深圳研究生院 | 研究员、助理教授、博士生导师 |
电子邮箱： liumengyuan@pku.edu.cn
发表论文
| # | 作者 | 会议 | 期刊 | 论文名称 |
|---|---|---|---|
| 1 | Xinshun Wang, Peiming Li, Ziyi Wang, Zhongbin Fang, Zhichao Deng, Songtao Wu, Xiangtai Li, Mengyuan Liu (通讯) | CVPR'26 | Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation |
| 2 | Juyi Sheng, Ziyi Wang, Peiming Li, Mengyuan Liu (通讯) | AAAI'26 | MeanFlow Tames Policy Learning in 1-step for Robotic Manipulation |
| 3 | Yutian Zhang, Jianyu Zhang, Mengyuan Liu (通讯) | ICRA'26 | Find Anything Like Humans: Online Semantic Mapping And Coarse-to-fine Navigation in Dynamic Environments |
| 4 | Mengyuan Liu, Jinfu Liu, Yongkang Jiang, Bin He | TPAMI'26 | Heatmap Pooling Network for Action Recognition from RGB Videos |
| 5 | Mengyuan Liu, Zhongbin Fang, Xia Li, Joachim M. Buhmann, Deheng Ye, Xiangtai Li, Chen Change Loy | IJCV'26 | Point-In-Context: Understanding Point Cloud via In-Context Learning |
| 6 | Ziyi Wang, Peiming Li, Hong Liu, Zhichao Deng, Can Wang, Jun Liu, Junsong Yuan, Mengyuan Liu (通讯) | ICCV'25 | Recognizing Actions from Robotic View for Natural Human-Robot Interaction |
| 7 | Peiming Li, Ziyi Wang, Yulin Yuan, Hong Liu, Xiangming Meng, Junsong Yuan, Mengyuan Liu (通讯) | ICCV'25 | UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling |
| 8 | Wenhao Li, Mengyuan Liu (共同通讯), Hong Liu, Pichao Wang, Shijian Lu, Nicu Sebe | TPAMI'25 | H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers |
| 9 | Mengyuan Liu, Jiajie Liu, Jinyan Zhang, Wenhao Li, Junsong Yuan | TIP'25 | PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation |
| 10 | Jialun Cai, Mengyuan Liu (通讯), Hong Liu, Shuheng Zhou, Wenhao Li | TIP'25 | NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation |
| 11 | Ti Wang, Mengyuan Liu (通讯), Hong Liu, Bin Ren, Yingxuan You, Wenhao Li, Nicu Sebe, Xia Li | TMM'25 | Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation |
| 12 | Wenhao Li, Mengyuan Liu (通讯), Hong Liu, Pichao Wang, Jialun Cai, Nicu Sebe | CVPR'24 | Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation (Highlight) |
| 13 | Xinshun Wang, Zhongbin Fang, Xia Li, Xiangtai Li, Chen Chen, Mengyuan Liu (通讯) | CVPR'24 | Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning |
| 14 | Yuhang Wen, Mengyuan Liu (通讯), Songtao Wu, Beichen Ding | NeurIPS'24 | CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition |
| 15 | Sheng Yan, Mengyuan Liu (通讯), Yong Wang, Yang Liu, Hong Liu | TCSVT'24 | MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions |
| 16 | Wanying Zhang, Mengyuan Liu (通讯), Xinshun Wang, Shen Zhao, Can Wang | TCSVT'24 | CHAMP: A Large-Scale Dataset for Skeleton-Based Composite HumAn Motion Prediction |
| 17 | Yi Zhang, Xinhua Xu, Youjun Zhao, Yuhang Wen, Zixuan Tang, Mengyuan Liu (通讯) | TIP'24 | Facial Prior Guided Micro-Expression Generation |
| 18 | Xinshun Wang, Wanying Zhang, Can Wang, Yuan Gao, Mengyuan Liu (通讯) | TIP'24 | Dynamic Dense Graph Convolutional Network for Skeleton-Based Human Motion Prediction |
| 19 | Zhongbin Fang, Xiangtai Li, Xia Li, Joachim Buhmann, Chen Change Loy, Mengyuan Liu (通讯) | NeurIPS'23 | Explore In-Context Learning for 3D Point Cloud Understanding (Spotlight) |
| 20 | Jinfu Liu, Xinshun Wang, Can Wang, Yuan Gao, Mengyuan Liu (通讯) | TMM'23 | Temporal Decoupling Graph Convolutional Network for Skeleton-Based Gesture Recognition |
| 21 | Yang Liu, Hong Liu, Huaqiu Wang, Fanyang Meng, Mengyuan Liu (通讯) | TNNLS'23 | BCAN: Bidirectional Correct Attention Network for Cross-Modal Retrieval |