About Me
I am a Ph.D. student in Computer Science at 
Harbin Institute of Technology, Shenzhen, jointly trained at 
SLAI (深圳河套学院). My advisors are Prof. Yongbing Zhang (张永兵) at HIT Shenzhen and Prof. Zhiguo Zhang (张治国) at SLAI.
My research interests lie in AI for Science, particularly foundation models, world models, and multimodal learning. I am interested in models that learn transferable representations and predict how complex systems behave, including under changing conditions and interventions. I currently explore these questions in biology and biomedicine.
My current work includes whole-slide image encoding and spatial molecular modeling. Previously, I worked on multimodal medical image analysis and interned at 
United Imaging Healthcare on medical report generation.
Current focus: AI for Science · Foundation Models · World Models
Google Scholar ↗Web CV ↗Email ↗
🧠 Foundation Models
Transferable representations · Generalization
🌐 World Models
System dynamics · Perturbation responses
🔗 Multimodal Learning
Images · Molecular measurements · Scientific data
News
- DSB-Net, our work on decoupled shape–boundary learning, is under review at ICASSP.
- Submitted a manuscript on whole-slide image encoding to ISBI.
- Started my Ph.D. at HIT Shenzhen, jointly trained at SLAI.
- PolarDETR was published at MICCAI 2025.
Selected Publications
Full list on Scholar ↗
Cancellous bone segmentation network in cone beam CT images for post-orthognathic assessment of condylar resorption
Dentomaxillofacial Radiology, 2026 · 55(3): 267–275
A dual-branch fusion network uses cancellous-edge localization as an auxiliary task to improve CBCT bone segmentation.
Paper DOI: 10.1093/dmfr/twaf081
PolarDETR: Enhancing Interpretability in Multi-modal Methods for Jawbone Lesion Detection in CBCT
MICCAI, 2025 · Medical Image Computing and Computer Assisted Intervention
A multimodal detection framework using polar-coordinate positional priors, with metrics for structural consistency and image–text alignment.
Paper DOI: 10.1007/978-3-032-04927-8_48
Research & Projects
Whole-Slide Image Encoding
Submitted to ISBIResearch project
Visual representation learning and image encoding for whole-slide pathology images. The manuscript is under review.
Spatial Evidence
In progressResearch project
Ongoing research on learning from spatial molecular measurements.
Virtual Cells & Cell Foundation Models
ExplorationResearch direction
Exploring models of cellular states and responses to perturbations, including participation in a team-based virtual-cell modeling competition.
DSB-Net: Shape–Boundary Decoupling
ICASSP · Under reviewResearch manuscript · Co-first author
Decouples shape-prior learning from boundary-detail refinement for segmentation in ambiguous medical images.
Experience
United Imaging Healthcare
Algorithm Research Intern · Central Research Institute, LLM Lab
- Led work on image-grounded multimodal medical report generation.
- Contributed to head CT report generation, including image–text data preparation and instruction-tuning design.
Education
Harbin Institute of Technology, Shenzhen SLAI
Ph.D. student in Computer Science · Joint training
- Advisor at HIT Shenzhen: Prof. Yongbing Zhang (张永兵).
- Advisor at SLAI: Prof. Zhiguo Zhang (张治国).
Beijing Jiaotong University
M.Eng. in Electronic Information
Beijing Jiaotong University
B.Eng. in Information Engineering
Site Visitors
The optional map loads a third-party service only after you choose to load it. Provider privacy information ↗
Contact
I welcome conversations about AI for Science, research collaborations, and visiting opportunities.