About
I am an undergraduate at Fudan University (GPA 3.84/4.00). Currently, I am an intern at Joy Future Academy, JD, researching streaming audio-visual generation, DMD distillation algorithms, and world models with world model memory. Our team's JoyAI-Echo achieves minute-level coherent audio-video story generation, and my OmniForcing (ECCV 2026, cited by the Alibaba Wan Team) was presented as an invited talk at Lightricks (LTX-Video Team) to their CTO and Director of GenAI Research. In 2025, I was an exchange student at UNC Chapel Hill, supervised by Prof. Huaxiu Yao, where I contributed to SimpleMem (ICML 2026) based on deep analysis of long-term conversation characteristics and memory structures.
I am seeking PhD opportunities in multimodal foundation models for Fall 2027. I aspire to conduct research grounded in solid theoretical insights, with a particular interest in physically faithful world representations and enabling real-world tasks. If you have any relevant openings or would like to discuss potential collaboration, please feel free to contact me at yaofengsu@outlook.com — I would truly appreciate it.
Research Interests
My research interest lies in multimodal generative models as a means to build faithful representations of the world. Through reinforcement learning, distillation, and agent frameworks, I have contributed to applications spanning audio-visual generation, autonomous driving, and video understanding. I am particularly drawn to developing principled approaches that bridge generative modeling with physically grounded world understanding.