I’m a second-year PhD student in Computer Science at Northwestern University, advised by Manling Li. I earned my master’s degree working with Mengyue Wu at Shanghai Jiao Tong University in the CSE Department, where I also completed a B.E. (Honors). My research spans multimodal learning, foundation models, and spatial reasoning. Early on, I studied representation learning for depression detection. I then focused on contrastive learning for robust, cross-modal representations. Recently, I’ve been exploring cross-modal (“X-modality”) interaction, where X can be vision, audio, and beyond. I have also been working on agentic training frameworks (e.g., RAGEN and VAGEN) for multi-turn reasoning. My current primary focus is spatial cognition in foundation models. For more information about me, please refer to my CV. Please feel free to contact me via email.