My primary research focus lies in Human-Centric Artificial Intelligence, with a particular emphasis on bridging the gap between advanced generative models and human emotional intelligence. I am passionate about exploring the frontiers of Multi-modal Large Language Models (MLLMs) and Vision-Language Models (VLMs) to create more intuitive and empathetic AI systems.

Currently, I am investigating the integration of Diffusion Models with Affective Computing to enable emotion-aware content generation. I am driven by the potential of cross-modal fusion techniques to enhance how machines perceive, understand, and interact with human nuances in real-world scenarios.