About Me

I am currently a Ph.D. student in the Department of Electrical and Computer Engineering at the University of Toronto supervised by Prof. Baochun Li. Prior to starting my Ph.D., I worked as a research assistant in Professor Chau Yuen’s Lab. I received my B.Sc. and M.S. degrees in Information and Communication Engineering from Xidian University, Xi’an, China. My research focuses on distributed computing, multimodal machine learning, and decision-making, as well as on the intersections among these fields.

Research Focus Currently, my research focuses on enhancing the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs) through prompting, fine-tuning, and post-training methods. One of my primary research projects involves integrating reinforcement learning (RL) and multi-agent RL algorithms to develop advanced reasoning-oriented LLMs and VLMs.

Research Application I am exploring how to apply LLMs and VLMs to address practical scientific problems in telecommunications. As an initial exploration, I have organized a dataset aimed at reliable multimodal process supervision for VLMs in telecommunications.

Academic Projects

• dmmrl: A lightweight platform for developing and evaluating RL-driven reasoning mechanisms in LLMs and VLMs.
• llmpebase: A platform for developing reasoning mechanisms in large language models.
• vggbase: A platform for designing and assessing image-text alignment methods.
• personalized fl: Implementations of diverse personalized federated learning (FL) methods.
• ssl fl: Implementations of self-supervised learning methods within the federated paradigm.

Research Highlights

• Perception: capturing explicit relationships for visual-language data in the world.
• Reasoning: building sequential decision-making algorithms for reliable problem-solving.
• Efficiency: enabling faster and secure perception and reasoning in large-scale networks.
• AI for Science: applying generative models to practical problems in telecommunications.