Postdoc Neurosymbolic Reasoning in Multimodal World Models

Are you passionate about cutting-edge research on multimodal reasoning, operating in an international research environment, and co-supervising PhD students? Then keep reading: this 2-year fully-funded postdoc position may be for you.

Postdoc Neurosymbolic Reasoning in Multimodal World Models

Your function

While the performance of multimodal world models has significantly improved, they still lack commonsense abstraction and reasoning capabilities. These models fail to capture the causal aspects of the physical and social world. To address the grand challenge of commonsense abstraction and reasoning with multimodal world models, we will explore methods to enhance their robustness, abstraction, and visual grounding abilities. We will focus on learning explicit, effective abstractions from limited human-labeled data, serving as dynamic, neurosymbolic world models. Following cognitive principles, we will evaluate these methods on tasks that require commonsense reasoning over space, time, and causality.

This project is funded by the NWO AiNed talent project “Human-centric AI with common sense” of Dr. Filip Ilievski (Learning and Reasoning, VU Amsterdam). The Postdoc will be co-supervised by Dr. Filip Ilievski, Dr. Emile van Krieken (Learning and Reasoning, VU Amsterdam), and Prof. Cees Snoek (Video & Image Sense Lab, UvA). The Postdoc will be part of ELLIS Unit Amsterdam.

Your duties

• to show independence in achieving research goals and willingness to collaborate and supervise PhD students working on multimodal abstraction, commonsense reasoning, and world models
• to invent, evaluate, and describe novel techniques for multimodal abstraction and explicit reasoning as dynamic, neurosymbolic world models
• to publish and present this research at international conferences, workshops, and journals
• to become an active member of the research community and to collaborate with other researchers, both in Amsterdam and internationally
• to contribute to teaching activities, such as lectures, lab courses, or supervising bachelor and master students
• to develop your portfolio and vision towards your next career position in academia

Your profile

• you have a PhD in Machine Learning, Computer Vision, Natural Language Processing, Neurosymbolic AI, or a closely related area
• you can invent and evaluate novel algorithms and present these orally and in writing
• you have a record of publishing in relevant, high-quality conferences or journals in the above fields
• you are eager to tackle fundamental challenges in the areas of multimodality, abstraction, commonsense reasoning, and neurosymbolic world models
• you can implement and evaluate commonsense reasoning methods with multimodal foundation models, e.g., using Python deep learning toolkits
• you can work well in teams and communicate effectively in written and spoken English

We realise that each individual brings a unique set of skills, expertise and mindset. Therefore we are happy to invite anyone who recognises themselves in the profile to apply, even if you do not meet all the requirements.

What do we offer?

A challenging position in a socially engaged organisation. At VU Amsterdam, you contribute to education, research and service for a better world. And that is valuable.

About the department

The VUA Department of Computer Science has approximately 250 members, including 50 tenured staff members and 40-50 PhD students.

Faculty of Science

Working at the Faculty of Science means collaborating with students, lecturers and researchers who are focused on their field, yet have a broad view of the world. We are proud of a positive and inclusive workplace culture within the faculty, where we work together with great energy and a pragmatic attitude to tackle social challenges. At the Faculty of Science, scientists and students work on fundamental and complex societal issues for a sustainable, healthy and just future.