Recent breakthroughs in Artificial Intelligence have led to the emergence of the first generation of foundation models capable of generalizing across tasks, domains, and modalities. These advances have opened up powerful new paradigms for solving complex, domain-specific problems through generalist models that can be efficiently fine-tuned for diverse applications. However, the promise of these models is limited by two key challenges: (i) their difficulty in robustly generalizing to new contexts and domains, and (ii) their limited capacity for reasoning and adapting over multimodal, spatio-temporal data streams.
This PhD project addresses these limitations by focusing on causal exploration, enabling agents to actively seek out informative interventions in order to learn the underlying structure of their environment. Rather than relying solely on passive data, the agent will experiment, hypothesize, and test causal relationships to construct more robust and transferable world models. This active, structured approach to learning is crucial for collecting fine-tuning data for flexible multimodal generalist foundation models (MGFMs) that can generalize to novel tasks and adapt to previously unseen settings autonomously through exploration.
Recent breakthroughs in Artificial Intelligence have led to the emergence of the first generation of foundation models capable of generalizing across tasks, domains, and modalities. These advances have opened up powerful new paradigms for solving complex, domain-specific problems through generalist models that can be efficiently fine-tuned for diverse applications. However, the promise of these models is limited by two key challenges: (i) their difficulty in robustly generalizing to new contexts and domains, and (ii) their limited capacity for reasoning and adapting over multimodal, spatio-temporal data streams.
This PhD project addresses these limitations by focusing on causal exploration, enabling agents to actively seek out informative interventions in order to learn the underlying structure of their environment. Rather than relying solely on passive data, the agent will experiment, hypothesize, and test causal relationships to construct more robust and transferable world models. This active, structured approach to learning is crucial for collecting fine-tuning data for flexible multimodal generalist foundation models (MGFMs) that can generalize to novel tasks and adapt to previously unseen settings autonomously through exploration.
You will conduct cutting-edge research at the intersection of deep reinforcement learning, causal representation learning, and multimodal foundation models. The aim is to develop “artificial scientist” agents capable of formulating and testing causal hypotheses through interaction, going beyond passive observation to active, grounded learning.
You will begin by designing reinforcement learning agents that explore complex environments starting from an incomplete or noisy causal graph extracted from a pretrained foundation model. These agents will need to reason, experiment, and adapt their behavior and world model by refining their causal understanding. As the project progresses, the insights and techniques developed will be used to inform new methods for fine-tuning multimodal generalist foundation models (MGFMs) to be causality consistent. Your work will contribute to the European Horizon ELLIOT project, which focuses on embedding spatial, temporal, object-level, and causal awareness into MGFMs.
This research is embedded in the Video & Image Sense lab at the University of Amsterdam, and you will be part of an interdisciplinary team contributing to the ELLIOT consortium, which includes 32 academic and industrial partners. ELLIOT aims to deliver open, reproducible foundation models and tools that benefit the wider European AI community.
Tasks and responsibilities:
Your profile
A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The preferred starting date is September 1st 2025. This should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.
The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 2,901 to € 3,707 (scale P). This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile PhD Candidate 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:
Are you curious to read more about our extensive package of secondary employment benefits, take a look here.
The Faculty of Science 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 position is with dr. Efstratios Gavves at the University of Amsterdam within VIS lab, co-led by dr. Andrii Zadaianchuk and dr. Christian Gumbsch. VIS lab is a world-leading lab on Computer Vision and Machine Learning, and has over 30 PhD students, postdoctoral researchers and faculty members working on a broad variety of deep learning, computer vision, and foundation model subjects, like self-supervised learning, diffusion models, and test-time generalization for perception tasks like object detection, instance segmentation and activity recognition. The position is also embedded in the European ELLIS Network of Excellence in AI.
You will conduct cutting-edge research at the intersection of deep reinforcement learning, causal representation learning, and multimodal foundation models. The aim is to develop “artificial scientist” agents capable of formulating and testing causal hypotheses through interaction, going beyond passive observation to active, grounded learning.
You will begin by designing reinforcement learning agents that explore complex environments starting from an incomplete or noisy causal graph extracted from a pretrained foundation model. These agents will need to reason, experiment, and adapt their behavior and world model by refining their causal understanding. As the project progresses, the insights and techniques developed will be used to inform new methods for fine-tuning multimodal generalist foundation models (MGFMs) to be causality consistent. Your work will contribute to the European Horizon ELLIOT project, which focuses on embedding spatial, temporal, object-level, and causal awareness into MGFMs.
This research is embedded in the Video & Image Sense lab at the University of Amsterdam, and you will be part of an interdisciplinary team contributing to the ELLIOT consortium, which includes 32 academic and industrial partners. ELLIOT aims to deliver open, reproducible foundation models and tools that benefit the wider European AI community.
Tasks and responsibilities:
Your profile
A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The preferred starting date is September 1st 2025. This should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.
The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 2,901 to € 3,707 (scale P). This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile PhD Candidate 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:
Are you curious to read more about our extensive package of secondary employment benefits, take a look here.
The Faculty of Science 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 position is with dr. Efstratios Gavves at the University of Amsterdam within VIS lab, co-led by dr. Andrii Zadaianchuk and dr. Christian Gumbsch. VIS lab is a world-leading lab on Computer Vision and Machine Learning, and has over 30 PhD students, postdoctoral researchers and faculty members working on a broad variety of deep learning, computer vision, and foundation model subjects, like self-supervised learning, diffusion models, and test-time generalization for perception tasks like object detection, instance segmentation and activity recognition. The position is also embedded in the European ELLIS Network of Excellence in AI.
If you feel the profile fits you, and you are interested in the job, we look forward to receiving your application. You can apply online via the button below. We accept applications until and including 30 July 2025. Applications should include the following information (all files besides your CV should be submitted in one single pdf file):
A knowledge security check can be part of the selection procedure (for details: national knowledge security guidelines).
Please use the CV field to upload your resume as a separate pdf document. Use the Cover Letter field to upload the other requested documents, including the motivation letter, as one single pdf file. Only complete applications received within the response period via the link below will be considered. The interviews for this position will be held in July and August. Do you have any questions or do you require additional information? Please contact: dr. Efstratios Gavves – [email protected]
If you feel the profile fits you, and you are interested in the job, we look forward to receiving your application. You can apply online via the button below. We accept applications until and including 30 July 2025. Applications should include the following information (all files besides your CV should be submitted in one single pdf file):
A knowledge security check can be part of the selection procedure (for details: national knowledge security guidelines).
Please use the CV field to upload your resume as a separate pdf document. Use the Cover Letter field to upload the other requested documents, including the motivation letter, as one single pdf file. Only complete applications received within the response period via the link below will be considered. The interviews for this position will be held in July and August. Do you have any questions or do you require additional information? Please contact: dr. Efstratios Gavves – [email protected]
We, and third parties, use cookies on our website. We use cookies to ensure that our website functions properly, to store your preferences, to gain insight into visitor behavior, but also for marketing and social media purposes (showing personalized advertisements). By clicking 'Accept', you agree to the use of all cookies. In our Cookie Statement. you can read more about the cookies we use and save or change your preferences. By clicking 'Refuse' you only agree to the use of functional cookies.