Research Internship at CKI - Actionable Knowledge Representation

Position: Research Internship at CKI

Project: Actionable Knowledge Representation

Scientific supervisor: Prof. Dr. Andrey Ustyuzhanin

Introduction to CKI:

The Constructor Knowledge Institute (CKI) intends to set the worldwide standard for research into Computer Science, AI and Machine Learning, Robotics, and Neuroscience, operating in strong contact with industry, and:

• Leveraging CS technologies to address challenges in various fields, delivering innovative solutions tailored to industry needs.
• Providing research opportunities, mentorship, and involvement in collaborative projects to young researchers and PhDs.
• Encouraging interdisciplinary research by fostering collaboration between diverse fields, emphasizing the integration of theoretical research with practical application

Project: Actionable Knowledge Representation

The goal of this project is to develop a novel approach for actionable knowledge representation that is flexible and adaptable to various tasks. The approach will focus on creating a knowledge representation framework that not only allows the storage and retrieval of information but also ensures that the representation can be dynamically adapted and utilized for different purposes. The project will explore ways to deal with key challenges in knowledge representation, such as hierarchy, composability, and coarse-graining, to provide a more robust and task-specific solution.

Challenges / key research questions:

• Design a knowledge representation framework that can be dynamically adapted to different tasks.
• Manage hierarchical structures and ensure efficient retrieval of knowledge.
• Balance generalization with specificity for various use cases.
• Address issues of composability and maintain the integrity of the representation.
• Ensure scalability and flexibility across diverse domains.

Requirements:

• Python skills
• Experience with AI libraries
• Prompt engineering
• Math and data processing skills are plus