Yicong joined Adobe Research in February 2025. He received his Ph.D. in December 2023 from the College of Engineering, Computing, and Cybernetics at the Australian National University, advised by Prof. Stephen Gould.

His research has spanned multimodal embodied AI, 3D reconstruction, and image and video generation.

Currently, he focuses on generative network architectures and modeling, including developing world models for real-time, interactable, and consistent video generation, advancing long-context modeling techniques (e.g., Test-Time Training), designing efficient linear-complexity models, and exploring the integration of diffusion and autoregressive approaches.

Visit Yicong’s homepage to learn more about his research and experience!