Summary
Guian Fang is a research scientist based in Singapore specializing in multimodal generative AI, with a focus on text-to-3D world and video generation. Over five years he has combined academic research roles across top institutions (NUS, MBZUAI, UNC Chapel Hill, HKUST) with industry experience at Utopai Studios and Shanghai AI Lab, bridging cutting-edge research and applied systems. His work spans generative models, human-feedback reinforcement learning, and large language/model integration for visual content, now being formalized in a PhD in Video Understanding and Generation at NUS. Notably, he rapidly transitions between academia and industry, suggesting both deep theoretical grounding and practical product-minded experimentation.
5 years of coding experience
1 year of employment as a software developer
Bachelor of Engineering, Intelligent Science and Technology, Bachelor of Engineering, Intelligent Science and Technology at Sun Yat-sen University
Doctor of Philosophy - PhD, Video Understanding and Generation, Doctor of Philosophy - PhD, Video Understanding and Generation at National University of Singapore