The next decade for Representation Learning will find Causality, Interactivity, and Embodiment in the centre, given also the impressive progress in 3D simulated. However, our causal representations are not yet mature enough to compete with the likes of self-supervised learning, which however, rely purely on correlations. What is more, our causal representations are not yet mature to account for all possible fine-grained interventions and interactions that a 3D World would require.

Are you passionate about bleeding edge research on Causal Representation Learning and with a knack towards Computer Vision and Embodied AI applications? Then this is the position for you!

We are looking for a postdoctoral researcher with expertise in Causal Representation Learning, Causality or Machine Learning to join a team of 15+ researchers (1+1 years contract); a team that is connected with the ELLIS Network of Excellence in AI; a team with consistent and strong presence in the top Machine Learning, as well as Computer Vision conferences and journals.

What are you going to do?
Causal Representation Learning is an excellent framework to enable embodied agents in 3D worlds with zero-shot and novel task capabilities, by discovering causal knowledge that applies to new settings, and by learning mechanisms on how to interact with novel environments.

In this position, we will start from our successful works on causal representation from spatiotemporal sequences, like CITRIS, iCITRIS, and the latest BISCUIT that works on full images. While these works lay down the foundations for causal representations that are learned from high-dimensional data like images, in a 3D World environment we require much more fine-grained and decomposable causal representations and mechanisms. The project can focus on a subset of the following key objectives, although research freedom is more than welcome:

• Learn to transfer causal priors from complex 3D world simulators to real data.
• Learn causal primitives (“skills”) that align with causal priors and interactions.
• Decompose known-by-demonstration complex tasks into simple causal skills.
• Compose causal skills for novel, zero-shot complex task learning.

Making 3D embodiment core to our proposal, we leverage simulated environments like AI2Thor, AIHabitat, ISAAC Sim, or even ObjectFolder with 3D meshes, videos, and tactile readings of real-world objects. We discover causal primitives that transfer better to the real world, e.g. world models, physics laws, and object affordances, compared to correlation-based distributed representations and domain adaptation.

The funding is from personal grants with little strings attached, and fundamental research is possible and desirable.

Tasks and responsibilities:

• Show independence in achieving research goals and willingness to collaborate and to supervise PhD students working on causal representation learning, deep learning, computer vision, dynamical and interactive systems;
• Contribute to a real-world showcase demo along the lines of the challenges in Embodied AI;
• Present research results at international conferences, workshops, and journals;
• Become an active member of the research community and to collaborate with other researchers, both within and outside the Informatics Institute;
• Contribute to teaching activities, such as lectures, lab courses, or supervising bachelor and master students.

Your experience and profile:

• A PhD in either an AI-related field (Causality, Machine Learning, Deep Learning, Computer Vision);
• Ability to invent and evaluate novel algorithm, and present these orally and in writing;
• Committed researcher, demonstrated by publications in the top machine learning, computer vision, or other top scientific conferences and journals;
• Ability to implement and evaluate machine learning algorithms in Python with deep learning toolkits (PyTorch, TensorFlow, Jax);
• Ability to work with 3D embodied simulators (or willing to learn);
• Ability to work well in teams and communicate fluently in written and spoken English.

We offer a temporary employment contract for 38 hours per week for a period of 12 months The preferred starting date is as soon as possible. If we assess your performance positive, your contract will be extended with 12 months.

The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 2,960 to € 4,670 (scale 10). UvA additionally offers an extensive package of secondary benefits, including 8% holiday allowance and a year-end bonus of 8.3%. The UFO profile Researcher 4 is applicable. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable.

Besides the salary and a vibrant and challenging environment at Science Park we offer you multiple fringe benefits:

• 232 holiday hours per year (based on fulltime) and extra holidays between Christmas and 1 January;
• Multiple courses to follow from our Teaching and Learning Centre;
• Multiple courses on topics such as leadership for academic staff;
• Multiple courses on topics such as time management, handling stress and an online learning platform with 100+ different courses;
• 7 weeks birth leave (partner leave) with 100% salary;
• Partly paid parental leave;
• The possibility to set up a workplace at home;
• A pension at ABP for which UvA pays two third part of the contribution;
• The possibility to follow courses to learn Dutch;
• Help with housing for a studio or small apartment when you’re moving from abroad.
• Are you curious to read more about our extensive package of secondary employment benefits, take a look here.

Faculty of Science

The University of Amsterdam (UvA) is the Netherlands' largest university, offering the widest range of academic programmes. At the UvA, 42,000 students, 6,000 staff members and 3,000 PhD candidates study and work in a diverse range of fields, connected by a culture of curiosity.

The Faculty of Science (FNWI) has a student body of around 8,000, as well as 1,800 members of staff working in education, research or support services. Researchers and students at the Faculty of Science are fascinated by every aspect of how the world works, be it elementary particles, the birth of the universe or the functioning of the brain.

The mission of the Informatics Institute (IvI) is to perform curiosity-driven and use-inspired fundamental research in Computer Science. The main research themes are Artificial Intelligence, Computational Science and Systems and Network Engineering. Our research involves complex information systems at large, with a focus on collaborative, data driven, computational and intelligent systems, all with a strong interactive component.

The Video & Image Sense lab (VIS) studies computer vision, deep learning and cognitive science, making sense of video and images with artificial and human intelligence. It positions itself within the AI research theme, with clear links to the Data Science theme of the Informatics Institute. The VIS Lab is strongly embedded in the larger UvA and Amsterdam artificial intelligence ecosystem with connections to multiple public-private Innovation Centres for AI (ICAI) labs and spin-off's including Kepler Vision Technologies and Ellogon.ai.

The position is with Dr Efstratios Gavves, Associate Professor in the Informatics Institute at the University of Amsterdam. Dr Gavves and ERC Starting Grant laureate, who is more than happy to help with mentoring on how to develop an excellent academic profile, including how to work on a vision, prepare proposals, and of course collaborate in excellent research. At the University of Amsterdam, we have an open and friendly attitude to open research, collaborations, and independent thinking.

Want to know more about our organisation? Read more about working at the University of Amsterdam.