I am Haoze Yu (于浩泽), an undergraduate student majoring in Computer Science & Technology at Harbin Institute of Technology, Shenzhen (HITsz), expected to graduate in June 2027.
My current research focuses on world models and AIGC. I am interested in understanding how generative systems model, simulate, and create complex worlds, and in developing reliable multimodal methods for generation, reasoning, evaluation, and trustworthy deployment.
- 🎓 B.Eng. in Computer Science & Technology, HITsz, 2023–2027 (expected)
- 📈 GPA: 3.94 / 4.0
- 🔬 Research interests: World Models · AIGC · Multimodal AI
I study models that learn representations of environments, dynamics, and interactions, with an interest in simulation, prediction, planning, and multimodal reasoning.
I explore generative models for controllable content creation, evaluation, and reliable deployment across image, video, audio, and language modalities.
I am interested in robustness, interpretability, and trustworthy evaluation for multimodal generative systems.
Project Lead · Harbin Institute of Technology, Shenzhen · Oct 2025 – Mar 2026
- Designed a multi-stage framework for multimodal forgery analysis using visual appearance, motion cues, style evolution, and audio-visual consistency.
- Focused on real/fake prediction, forged-region localization, and interpretable cause analysis.
Project Lead · Harbin Institute of Technology, Shenzhen · Dec 2024 – Jul 2025
- Designed a hierarchical framework for encrypted and malicious traffic analysis.
- Combined screening, attack-family classification, attribution, routing, and calibrated fusion.
- Three National-level Scholarships
- First-class Academic Scholarship, Harbin Institute of Technology (2025)
- Top 10 Youth Volunteers, HIT (2025)
- National Second Prize, National AI Competition for College Students
- Provincial First Prize, China Undergraduate Mathematical Contest in Modeling
- Programming: Python · C++ · C · Java
- Machine Learning: PyTorch · Transformer architectures · Model training · Evaluation & analysis
- LLM / Multimodal: Fine-tuning · Inference · Deployment · RAG pipelines · Multimodal models
- Systems: Linux · Git · Experiment reproduction · Scripting · RISC-V CPU design
| Project | Description |
|---|---|
| multimodal-document-reasoner | Multimodal document understanding and reasoning experiments. |
| aircraft-war-android | Native Android aircraft battle game with Java, SQLite, networking, audio, and LAN multiplayer. |
| -CPU- | CPU design project with single-cycle / pipelined implementations and RISC-V-style architecture experiments. |
| computer-science-skills-collection | Collection of computer science learning materials and engineering practice. |
Researching world models, AIGC, and reliable multimodal AI systems.