Ph.D. Student in Multimodal AI and AI4Earth
I am a Ph.D. student at Fudan University and Shanghai Artificial Intelligence Laboratory, working on multimodal learning, large vision-language systems, and AI agents for Earth science.
- Multimodal Learning
- Vision-Language Systems
- AI4Earth
- Datasets & Benchmarks
Featured Projects
Selected Publications
Self-evolving AI agent for climate-science workflows.
Large-scale, multi-view 3D human pose dataset and benchmark under real-world conditions.
Instruction-tuning dataset, framework, and benchmark for multimodal large language models.
Transformer-based weakly supervised object localization with implicit spatial calibration.
Reinforcement learning for flexible exposure bracketing selection in HDR imaging.
Biography
I am supervised by Prof. Tao Chen at Fudan University and mentored by Dr. Lei Bai at Shanghai Artificial Intelligence Laboratory.
My research builds reusable datasets, benchmarks, and agentic systems that connect real-world perception with scientific workflows.
Research Focus
Multimodal Foundation Models
Instruction tuning, evaluation, and extensible benchmarks for large vision-language and multimodal systems.
Real-world Perception Benchmarks
Large-scale data and benchmarks for robust 3D human perception in unconstrained environments.
AI4Earth and Scientific Agents
Agentic systems that support climate-science reasoning, tool use, and iterative scientific workflows.
Research Trajectory
2023 — Present
Ph.D. Student, Fudan University & Shanghai AI Lab
Advisor: Prof. Tao Chen; mentored by Dr. Lei Bai.
2021 — 2023
MPhil, The Chinese University of Hong Kong (Shenzhen)
Advisors: Prof. David Zhang Dapeng and Prof. Ruimao Zhang.
2020 — 2021
Computer Vision Researcher, Tetras.ai / SenseTime Group
Low-level vision and applied computer vision research.
Contact
Address: 701, Yunjin Road, Xuhui District, Shanghai, China