Microsoft Research Asia – Tokyo is committed to advancing cutting-edge AI technologies that enable deeper understanding and interaction with people, objects, and environments in the 3D real world. Our research spans a diverse range of areas, including computer vision, generative AI, 3D perception, and robotic action learning, among others relevant to Embodied AI. By pushing the boundaries of these domains, we aim to develop innovative solutions that bridge the gap between the digital and physical worlds, empowering AI systems to perceive, comprehend, and navigate complex real-world scenarios.

We are seeking a highly motivated and talented PhD student to join our team as a Research Intern. This internship offers a unique opportunity to work on cutting-edge research in the field of Vision-Language Models (VLMs), fundamental machine learning, computer vision, and Spatial AI, and Robotics, for realization of Embodied AI. The successful candidate will work together as a team of experienced researchers to tackle real-world challenges and contribute to the advancement of AI technologies.