- 😄 I am Zhongyu Yang and working as a Remote Research Intern at Vision-CAIR, King Abdullah University of Science and Technology (KAUST), supervised by Mohamed Elhoseiny. Prior to that, I earned a Bachelor of Science degree with a major in Mathematics and a minor in Management from Lanzhou University, China.
- 💡 I'm profoundly interested in Multimodal Large Language Model and Diffusion-based GenAI(e.g. 2D/3D AIGC, Medical Image Analysis and Digital Human). Recently, I focused on enhancing MLLM's reasoning via multi-prompts and Multi-modal token compression for efficient modeling.
- 🏀 I am a big fan of the Los Angeles Lakers!
- In my past research, I am most interested in 2D/3D AIGC. In the short term, I hope to make a Controllable and Editable Generative Model to better understand Multimodal input, not just the Prompt and Visual Encoder.
- My long-term research Goal is to develop Intelligent Machines that can actively perceive, analyze, and interpret human states, behaviors, and potential motivations in dynamic scenes.
- Looking for a PhD position and Research Intern position now.
- 📫 Contact me: Email