PhD Talent Shines at AI PhD Poster Day 2024
On the sunny day of 25 June, the AI PhD Poster Day 2024 took place in the beautiful Hortus Botanicus of TU Delft. This day offered a blooming opportunity for PhD students to showcase their AI-related research, and exchange ideas with their peers from different faculties, and a big range of AI Labs.
When showing all the AI successes from TU Delft, it is very important to include our PhD talent, and highlight the work they’re doing around both foundational work in machine learning or human-cantered AI, as well as the different contributions that AI makes to key scientific and societal domains. With this event, we provide a platform for early career researchers to network and exchange ideas, and offer them the opportunity to develop and practice key skills. Happy to see the amazing and innovative work done by these talented colleagues.
Geert Jan Houben, Pro Vice Rector Magnificus AI, Data, and Digitalisation
Congratulations to all of the 6 winners from 5 different labs across 4 faculties. Their research will be highlighted in the AI communication channels over the summer period, so keep an eye out for our YouTube, LinkedIn, X (Twitter), and new Instagram account!
Best pitch 2024
The PhDs had the opportunity to pitch their poster and discuss questions from peers within their category during the first half of the event. This was followed by a poster market with visiting faculty staff and fellow PhD researchers. To decide the winner for the best pitch, participating PhDs voted for their favourite pitch within one of three categories. The PhD with the most votes within their category won the best pitch prize.
These are the best pitches per category:
- Category: Machine Learning & Foundational AI techniques
Daniël Vos from the faculty of Electrical Engineering, Mathematics and Computer Science, Cyber Analytics Lab with his poster pitch “Optimal decision tree policies for Markov Decision Processes”. - Category: Human Centred AI Systems
Antonio Mone from the faculty of Electrical Engineering, Mathematics and Computer Science, AiBLE Lab with his poster pitch “Unsupervised Reward-Agnostic Clustering of Behavioral Trajectories for Multi-Intention Inverse Reinforcement Learning”. - Category: Applications of AI
Casper van Engelenburg from the faculty of Architecture and the Built Environment, AiDAPT Lab with his poster pitch “Self-Supervised Similarity Learning of Floor Layouts”.
Best posters 2024
The best posters were decided by a selected jury for the event: Holger Caeser (Assistant Professor at the faculty of Mechanical Engineering, ELLIS Delft Unit), Nazli Cila (Assistant Professor at Industrial Design Engineering, Lab Director of the AI DeMoS Lab), Caroline Duterloo (Innovation Manager AI for Energy & Sustainability and Health & Care), and Christine Bel (Innovation Manager AI for Peace, Justice and Security and for Technological Industry).
- Category: Machine Learning & Foundational AI techniques
Eva Memmel from the faculty of Mechanical Engineering, DeTAIL Lab with her poster “Position: Tensor Networks are a Valuable Asset for Green AI”.
Eva successfully illustrated the fundamental research on tensor networks in a very accessible way. Not only were the scientific aspects explained, but the need and use of this research were clearly pointed out to fellow scientists and laymen.
Christine Bel, Innovation Manager AI for Peace, Justice and Security and for Technological Industry
- Category: Human Centred AI Systems
Amir Homayounirad from the faculty of Electrical Engineering, Mathematics and Computer Science, AiBLE Lab with his poster “Subjectivity Matters: A Hybrid (Human + AI) Method to Support the Identification and Representation of Subjective Values Behind Arguments”.
Amir incorporated the nuanced ways in which people perceive things into AI systems by integrating human values. The importance and impact of this approach were also explained in an accessible manner.”
Nazli Cila, Assistant Professor at Industrial Design Engineering, Lab Director of the AI DeMoS Lab
- Category: Applications of AI
Alexander Garzón Díaz from the faculty of Civil Engineering and Geosciences, AidroLab with his poster “Autoregressive Graph Neural Network for Emulating Stormwater Drainage Simulations”.
Alex's poster impressed the jury with its clear structure, effectively introducing the problem setting, methodology, results, and their implications. The detailed analysis considered performance in the target domain and the potential for generalization to other domains. The topic of stormwater drainage systems is both an intriguing application and highly relevant to our society.
Holger Caeser, Assistant Professor at the faculty of Mechanical Engineering, ELLIS Delft Unit
About the TU Delft AI Labs
On this sunny day, many of the 24 TU Delft AI Labs, ELLIS faculty members, and some ICAI Labs were represented by their PhD students. All of these labs and teams are committed to education, research and innovation in AI, data and digitalisation.
The 24 TU Delft AIlabs embody the bridge between research 'in' and 'with' AI, data and digitalisation. They foster cross-fertilisation between talent and expertise, working to increase the impact of AI in the fields of applied sciences, design techniques and society. Because of the TU Delft AI Labs & Talent Programme, academic faculty members and PhD students work together in each TU Delft AI Lab. The aim of this university-wide talent programme is to accelerate research in all relevant scientific disciplines and to increase educational capacity.
Take a look back at the AI PhD Poster Event 2024
About TU Delft | AI Initiative
AI, data and digitalisation are becoming increasingly important for solving major scientific and social issues. TU Delft is pursuing many strands of AI research, both ‘in AI’ and ‘with AI’. The role of AI technologies is also growing across our education and innovation activities. TU Delft aims to provide every student with AI education that embraces both ‘WITH’ and ‘IN’ learning. By equipping every student with a better and wider understanding, we can together build a society that’s capable of integrating AI responsibly and successfully. The TU Delft AI Initiative coordinates various activities and functions, providing a central platform for AI, data and digitalization-related research, for education and for innovation. It allows eight TU Delft faculties to collaborate intensively with multiple partners.