CV
Summary
M.Sc. Student in Informatics (AI) at University of Zurich (UZH). Interested in Computer Vision, Robotics, and Multimodal Models.
Education
- Informatics (Major: Artificial Intelligence, Minor: Data Science)PresentUniversity of Zurich (UZH)GPA: 5.57/6Courses: Data Science, Machine Learning for Natural Language Processing, Vision Algorithms for Mobile Robotics, ETHZ 3D Vision, ETHZ Virtual Reality
- Artificial Intelligence2024-06-01Nanjing University of Information Science and Technology (NUIST)GPA: 87.6/100
Work Experience
- Student Researcher2025-03-01 - 2026-02-01Computer Vision and Geometry Group (ETHZ CVG)Reproduced and improved GS-LIVO to achieve better geometric accuracy and mapping efficiency, reaching SOTA performance.
- Student Researcher2025-02-01 - 2026-01-01Robotics and Perception Group (UZH RPG)Conducted autoregressive pre-training on multimodal data, significantly improving the performance and robustness of downstream vision and control tasks.
- Computer Vision Algorithm Intern2023-07-01 - 2023-10-01IntSig Information Co., Ltd.Developed object detection algorithms based on improved DETR series architectures.
Skills
Robotics
- Robot Arm
- MuJoCo
- RL/IL
- ROS2
Computer Vision
- SLAM
- 3DGS
- Object Detection
- DETR
- GS-LIVO
Models
- VLA
- LLM
- Generative Models
- Diffusion
- Multimodal
Publications
- Generative Event Pretraining with Foundation Model Alignment2026CVPRProposed a multimodal pre-training method combining images and event cameras, achieving SOTA performance.
- Memory Over Maps: 3D Object Localization Without Reconstruction2026IROSResponsible for 3D object localization (query input, 3D position output) and efficiency analysis. Ultimately deployed on the Boston Dynamics Spot robot dog.
- Fuse Tune: Hierarchical Decoder Towards Efficient Transfer Learning2023PRCVProposed an efficient transfer learning method that eliminates the need for backbone network backpropagation.
Portfolio
- Real-time Visual-Inertial-LiDAR Gaussian Splatting SLAMPortfolioReproduced and improved GS-LIVO to achieve better geometric accuracy and mapping efficiency, reaching SOTA performance.
- Event Camera-Enhanced Robot Motor Control PoliciesPortfolioConducted autoregressive pre-training on multimodal data, significantly improving the performance and robustness of downstream vision and control tasks.