Key Responsibilities

• During the internship, you are expected to develop algorithms to advance research in embodied AI navigation using cognitive maps and/or exploration strategies for semantic map construction. Potential research topics include (but are not limited to):
  • Leveraging spatial memory to support short- and long-horizon navigation tasks under natural-language or multimodal instructions.
  • Investigating methods for lifelong learning, where agents incrementally update spatial memory during online exploration.
  • Developing approaches for reasoning-driven navigation, including semantic grounding of objects and scenes without costly 3D reconstruction.
  • Designing and evaluating benchmarks and metrics for lifelong embodied navigation.
  • Supporting the development of prototypes and demonstrations showcasing navigation capabilities in complex environments.
  • Contributing to a portfolio of academic publications, patents, and research deliverables to demonstrate impact.

Minimum Qualifications

• The candidate should be enrolled in a Master's or PhD program in Computer Science or a related field, or they must have recently completed their degree.
• Strong research experience in multimodal learning, computer vision, machine learning, and/or robotics.
• Experience in open-source deep learning frameworks such as PyTorch or Tensorflow.
• Proficiency with Python or C++.

Bonus Qualifications

• ​Experience in one or more of the following: generative models, vision language models, sequential decision making, embodied AI, reinforcement learning, robotics manipulation or navigation.
• Publications in top-tier conferences (e.g., CVPR, ICCV, ECCV, WACV, ICML, NeurIPS, ICLR, ICRA, IROS, etc.)