“We come from different universities and have a passion for research in the field of artificial intelligence,Our research direction focuses on advancing the field of artificial intelligence while prioritizing ethical considerations and practical applications. By emphasizing consistency, fairness, interdisciplinary collaboration, and robustness, we aim to contribute to the development of artificial intelligence technologies that are both powerful and responsible, ensuring they earn public trust.”
One of the primary challenges we face in AI development is aligning model objectives with human preferences. Understanding what constitutes a model's goal and how to refine these objectives through techniques such as prompt design and fine-tuning is crucial. Our aim is to ensure that AI systems act in ways that are beneficial and aligned with human values.