Xudong Wang

About Me

I’m a second-year Ph.D. candidate in Pattern Recognition and Intelligent Systems at State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences (SIA) & University of Chinese Academy of Sciences (UCAS) under the supervision of Prof. Zhi Han. Before UCAS, I received my bachelor’s degree in Jun. 2022 at North University of China. I am a selected participant in the Doctoral Student Program of the Young S&T Talents Cultivation Project, CAST. Currently I am a visiting PhD student at LV Robotics Lab at National University of Singapore (NUS) supervised by Prof. Shuicheng Yan.

My research focuses on Robotic Learning, Embodied AI, and Computer Vision. I serve as CAA, CIE, CSIG, AAAI Member and the reviewer for several conferences and journals such as ICLR, ICML, NeurIPS, CVPR, ICCV, ACM MM, AAAI, ICME and TMLR, IEEE TCYB, TIP, TNNLS, TII, RAL, I am also honored to have been awarded the Gold Reviewer Award for ICML 2026.

王旭东，机器人与智能系统全国重点实验室博士研究生，中国科协青年科技人才培育工程博士生专项计划入选者，在人工智能与智能机器人领域发表CCF-A类学术论文10余篇，包括ICLR、CVPR、AAAI、TIP、TMM等。代招实习生与合作交流，欢迎联系：wangxudong@sia.cn

Uni-SkillEvolver, Lifelong Robotic Skills Learning [Project Page]

News

[Jul. 2026] We provide a comprehensive survey for Vision-and-Language Navigation, please refer to From Instruction Following to Cognitive Navigation: A Survey on the Evolution of Vision-and-Language Navigation.
[Jun. 2026] I am honored to have been awarded the Jiang Xinsong Young Talent Fund!
[May. 2026] I am honored to have been awarded the Government-sponsored overseas study funding by the China Scholarship Council (CSC)!
[May. 2026] I am honored to have been awarded the Gold Reviewer Award for ICML 2026!
[Mar. 2026] We provide a comprehensive survey for World Models, please refer to Learning to Model the World.
[Feb. 2026] One Co-author paper about Continual Video Instance Segmentation has been accepted by IEEE Transactions on Image Processing (CCF-A, Q1), congratulations to Baichen and Qi Lyu!
[Feb. 2026] One Co-first-author paper about Lifelong Robotic Manipulation Learning has been accepted by IEEE CVPR 2026 (Core A*, CCF-A), thanks for co-authors!
[Jan. 2026] One Co-author paper about Tensor Recovery has been accepted by ICLR 2026 (CCF-A), congratulations to Zhiyu!
[Jan. 2026] Two Co-first-author paper about Lifelong Robotic Embodied Navigation and All-day Lifelong Robotic Navigation has been accepted by ICLR 2026 (CCF-A), thanks for co-authors!
[Dec. 2025] I am honored to have been selected for the Doctoral Student Program of the Young S&T Talents Cultivation Project, CAST!
[Nov. 2025] One first-author paper about Robotic Harsh Environment Perception has been accepted by IEEE Transactions on Multimedia (CCF-A, Q1), thanks for co-authors!
[Oct. 2025] Two Co-first-author paper about Robotic Manipulation Skills Lifelong Learning and Continual T2V Customization has been accepted by AAAI 2026 (Core A*, CCF-A), and one corresponding author paper about Long-Horizon Vision-Language Navigation has been accepted by AAAI 2026 (Core A*, CCF-A), thanks for co-authors!
[Oct. 2024] It’s my first time to go abroad (Melbourne, Australia) and give a poster presentation at an international academic conference (ACM MM 2024). What an amazing experience!
[Sept. 2024] I join in UCAS and become a first-year PhD student!
[Jul. 2024] One first-author paper about Robotic Open-World Perception has been accepted by ACM MM 2024 (Core A*, CCF-A), thanks for co-authors!
[Mar. 2024] One first-author paper about Real-Time Image Dehazing has been accepted by IEEE Transactions on Emerging Topics in Computational Intelligence (Q1), thanks for co-authors!
[Jul. 2023] It’s my first time to give a oral presentation at an international academic conference (ICIRA 2023).
[Jun. 2023] One first-author paper about Robotic Harsh Environment Perception has been accepted by ICIRA 2023 (Oral Presentation), thanks for co-authors!
[Sept. 2022] I join in UCAS and become a first-year M.S. student!

Selected Publications

Remark: Co-first Authors (†), Corresponding Author (#).

Kailin Lyu, et al. From Instruction Following to Cognitive Navigation: A Survey on the Evolution of Vision-and-Language Navigation. Preprints 2026.
Jiahua Dong†, Qi Lyu†, Baichen Liu#, Xudong Wang, Wenqi Liang, Duzhen Zhang, Jiahang Tu, Hongliu Li, Hanbin Zhao, Henghui Ding, Yulun Zhang, Zhi Han#, Nicu Sebe, Fahad Shahbaz Khan, Salman Khan, Mubarak Shan, Philip Torr, Ming-Hsuan Yang, Dacheng Tao. Learning to Model the World: A Survey of World Models in Artificial Intelligence. Preprints 2026.
Baichen Liu, Qi Lyu, Xudong Wang, Jiahua Dong, Lianqing Liu, Zhi Han. CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation. IEEE Transactions on Image Processing, T-IP 2026.
Jiahua Dong†, Xudong Wang†, Zebin Han, Wenqi Liang, Duzhen Zhang, Meng Cao, Nicu Sebe, Ivan Laptev, Zhi Han#, Fahad Shahbaz Khan, Salman Khan. Continual Vision-Language Action Learning in Robotic Manipulation. Conference on Computer Vision and Pattern Recognition, CVPR 2026.
Zhiyu Liu, Haobo Geng, Xudong Wang, Yandong Tang, Zhi Han, Yao Wang. The Power of Small Initialization in Noisy Low-Tubal-Rank Tensor Recovery. International Conference on Learning Representations, ICLR 2026.
Xudong Wang†, Jiahua Dong†, Baichen Liu#, Qi Lyu, Lianqing Liu, Zhi Han#. Lifelong Embodied Navigation Learning. International Conference on Learning Representations, ICLR 2026.
Xudong Wang†, Gan Li†, Zhiyu Liu, Yao Wang, Lianqing Liu, Zhi Han#. All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation. International Conference on Learning Representations, ICLR 2026.
Xudong Wang†, Zebin Han†, Zhiyu Liu, Gan Li, Jiahua Dong, Baichen Liu, Lianqing Liu, Zhi Han#. Lifelong Language-Conditioned Robotic Manipulation Learning. AAAI Conference on Artificial Intelligence, AAAI 2026.
Zebin Han, Xudong Wang#, Baichen Liu, Qi Lyu, Zhenduo Shang, Jiahua Dong, Lianqing Liu, Zhi Han. SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning. AAAI Conference on Artificial Intelligence, AAAI 2026.
Jiahua Dong†, Xudong Wang†, Wenqi Lian, Zongyan Han, Meng Cao, Duzhen Zhang, Hanbin Zhao, Zhi Han#, Salman Khan, Fahad Shahbaz Khan. Bring Your Dreams to Life: Continual Text-to-Video Customization. AAAI Conference on Artificial Intelligence, AAAI 2026.
Xudong Wang, Xi’ai Chen#, Huijie Fan, Weihong Ren, Shuai Wang, Yandong Tang, Zhi Han. “Seeing Only the Focus: RGB-T Object-Aware Region Enhancement for Object Detection in Harsh Environments”. IEEE Transactions on Multimedia, T-MM 2026.
Xudong Wang, Weihong Ren, Xi’ai Chen#, Huijie Fan, Yandong Tang, Zhi Han. Uni-YOLO: Vision-Language Model-Guided YOLO for Robust and Fast Universal Detection in the Open World. ACM International Conference on Multimedia, MM 2024.
Xudong Wang, Xi’ai Chen#, Weihong Ren, Zhi Han, Huijie Fan, Yandong Tang, Lianqing Liu. Compensation Atmospheric Scattering Model and Two-Branch Network for Single Image Dehazing. IEEE Transactions on Emerging Topics in Computational Intelligence, T-ETCI 2024.
Xudong Wang, Xi’ai Chen#, Feifan Wang, Chonglong Xu, Yandong Tang. Image Recovery and Object Detection Integrated Algorithms for Robots in Harsh Battlefield Environments. International Conference on Intelligent Robotics and Applications, ICIRA 2023 (Oral).