Liyuan Wang Posted Aug 1, 2025 Homepage Liyuan Wang Assistant Professor @ THU Co-Authored Publications Guanglong Sun, Kanglei Zhou, Liyuan Wang, Qi Cheng, Hongwei Yan, Shuang Cui, Hang Su, Jun Zhu, Yi Zhong (2026). MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning. arXiv preprint arXiv:2609.05075. Cite PDF arXiv GitHub Kanglei Zhou, Chunyan Lan, Dongyang Li, Jun Zhu, Liyuan Wang (2026). ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding. arXiv preprint arXiv:2609.05094. Cite PDF arXiv Kanglei Zhou, Ruizhi Cai, Xinning Wang, Yijian Zheng, Liyuan Wang, Jianguo Li, Xiaohui Liang (2026). Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment. International Journal of Computer Vision. Cite PDF DOI arXiv Kanglei Zhou, Ruizhi Cai, Liyuan Wang, Hubert P. H. Shum, Xiaohui Liang (2026). A Comprehensive Survey of Action Quality Assessment: Method and Benchmark. Pattern Recognition. Cite PDF Project DOI GitHub arXiv Hongwei Yan, Kanglei Zhou, Yuchen Liu, Qingyu Shi, Yi Zhong, Liyuan Wang (2026). CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning. International Conference on Machine Learning. Cite PDF GitHub OpenReview Kanglei Zhou, Chang Li, Qingyi Pan, Liyuan Wang (2026). BriMA: Bridged Modality Adaptation for Multi-Modal Continual Action Quality Assessment. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Cite PDF GitHub arXiv Yuwen Tao, Kanglei Zhou, Chang Li, Liyuan Wang (2026). Geometry-Aware Cross-Modal Graph Alignment for Referring Segmentation in 3D Gaussian Splatting. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Cite PDF Hongwei Yan, Guanglong Sun, Kanglei Zhou, Qian Li, Liyuan Wang, Yi Zhong (2026). FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning. International Conference on Learning Representations. Cite PDF GitHub arXiv OpenReview Chang Li, Kanglei Zhou, Liyuan Wang (2026). PACE: Pretrained Audio Continual Learning. International Conference on Learning Representations. Cite PDF arXiv OpenReview Kanglei Zhou, Zikai Hao, Liyuan Wang, Xiaohui Liang (2025). Adaptive Score Alignment Learning for Continual Perceptual Quality Assessment of 360-Degree Videos in Virtual Reality. IEEE Transactions on Visualization and Computer Graphics, VR 2025 Oral. Cite PDF DOI GitHub arXiv Bilibili Oral Presentation Kanglei Zhou, Qingyi Pan, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Xiaohui Liang, Liyuan Wang (2025). Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization. arXiv Preprint. Cite PDF GitHub arXiv Kanglei Zhou, Liyuan Wang, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Jianguo Li, Xiaohui Liang (2024). MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment. The 18th European Conference on Computer Vision, Oral, ~2.3%. Cite PDF Poster Slides DOI GitHub arXiv Oral Presentation Kanglei Zhou, Junlin Li, Ruizhi Cai, Liyuan Wang, Xinxing Zhang, Xiaohui Liang (2024). CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment. The 33rd International Joint Conference on Artificial Intelligence. Cite PDF DOI GitHub arXiv Supervisor
