About Me
I am a Research Fellow at Nanyang Technological University (NTU), Singapore. My research focuses on embodied intelligence and robot perception, with the goal of enabling robots to understand their surroundings, localize themselves, and act reliably in the physical world.
Previously, I was an AI Researcher in Embodied Robotics at Sony. I returned to NTU to lay the groundwork for a robotics startup. Earlier at NTU, I worked at the Hyundai–NTU–A*STAR Corporate Lab with Prof. Kong Wai-Kin Adams and led the SLAM research group at HESL, CCDS under Prof. Lam Siew Kei.
I received my Ph.D. from NTU in January 2026, supervised by Prof. Lam Siew Kei at CCDS. I earned my M.S. in Electronic Information Engineering from City University of Hong Kong in October 2019, supervised by Prof. So Hing Cheung (IEEE Fellow).
Earlier in my career, I worked as an Algorithm Engineer at CamSense (欢创科技) (2017–2018) and an Embedded Software Engineer at DJI RoboMaster (2016–2017). CamSense is now listed on the Hong Kong Stock Exchange (06802.HK).
Research Interests
- Embodied AI: Vision-Language-Action (VLA) models and AI for robotics.
- Robot Localization & Perception: visual SLAM and visual place recognition (VPR).
News
Congrats Wenyang! Our work on DriftAD: Visually-Guided Text Drift for Few-Shot Industrial Anomaly Detection has been accepted to ACM MM 2026.
One paper has been accepted to IROS 2026.
I’ve passed my PhD Oral Defence.
I’ve started a new role as a Research Associate at the Hyundai-NTU-A*STAR Corporate Lab.
Congrats Gao Ye! Our work on Motion-Feat: Motion Blur-Aware Local Feature Description for Image Matching has been accepted to IROS 2025.
Earlier news
Congrats Nanhua! Our work on SHAA: Spatial Hybrid Attention Network with Adaptive Cross-Entropy Loss Function for UAV-view Geo-localization has been accepted to IEEE T-CSVT.
I’ve started part-time teaching the undergraduate course SC3000/CZ3005 Artificial Intelligence at CCDS, NTU.
Our work on CurricularVPR: Curricular Contrastive Loss for Visual Place Recognition has been accepted to IROS 2024.
Our work on Training-Free Attentive-Patch Selection for Visual Place Recognition has been accepted to IROS 2023.
Public Service
Conference Reviewer
- 2027: ICRA, AAAI
- 2026: ECCV, AAAI, IROS