Our lab is advancing research in the development of vision-language-action models that enable agents to perceive, understand, and act upon their surroundings. We aim to create systems capable of comprehending multimodal sensory inputs and performing tasks in dynamic, real-world environments. By integrating vision and language with action-oriented learning, our research aspires to facilitate nuanced interactions and responsive behaviors that align with human intentions and natural communication patterns. We focus on enhancing the model's spatial awareness, contextual understanding, and adaptability, thereby equipping AI agents with the ability to execute complex, sequential tasks autonomously. Current projects involve developing agents that can interpret and respond to human instructions and adapt their behaviors based on environmental feedback.

Our lab is dedicated to advancing Multimodal AI, focusing on the seamless integration of diverse data types, such as text, images, audio, and sensory inputs, to enable more comprehensive and context-aware AI systems. By unifying multiple data sources, we aim to create models that can interpret complex scenarios and produce insights or actions that reflect a deeper understanding of real-world situations. Our research emphasizes improving the coordination between these modalities, allowing AI to discern nuanced relationships, such as associating visual cues with linguistic context or correlating audio patterns with specific environmental states.

Responsible AI refers to the development, deployment, and use of AI technologies in a manner that prioritizes ethical considerations, fairness, transparency, and accountability. This approach recognizes the potential impact of AI on individuals and society, emphasizing the need for responsible and inclusive practices throughout the AI lifecycle. Our research mainly focuses on developing techniques to identify and address biases in AI models, promoting fairness and preventing discrimination across diverse demographic groups, and also conducting assessments to understand and mitigate the broader societal impact of AI applications, including considerations of job displacement, economic implications, and social equality.

Medical AI involves the development and application of AI technologies with a primary focus on enhancing healthcare outcomes and prioritizing the well-being of individuals. Medical AI mainly seeks to augment the capabilities of healthcare professionals, improve diagnostic accuracy, streamline treatment planning, and personalize patient care. Currently, we are working on implementing AI-driven natural language processing techniques to extract valuable insights from unstructured clinical notes, medical literature, and patient communications and also utilizing AI to predict disease progression, identify at-risk populations, and optimize preventive interventions, leading to more proactive and personalized healthcare.

Gaming AI goes beyond rule-based systems to maximize the convenience and enjoyment of games through large multi-modal models. This AI technology empowers game developers to craft and deliver more immersive experiences for players. As AI technology continues to advance and mature, we anticipate it will ignite the imagination and ingenuity of both game designers and players. Gaming AI encompasses various domains, including voice AI, chatbots, and diverse generative AI applications. For instance, a voice AI generator and gaming chatbots can provide real-time assistance to gamers and help them build their unique worlds. With AI and automation, the gaming experience will be elevated to unprecedented levels.