This Data Challenge asks data science problems in the context of urban energy sustainability. More precisely, the focus of the challenge is on sensor data from a smart-building located on a university campus. The building is a so-called multi-tenant building, which means that it is used by different types of organizations. The Data Challenge addressed […]
Mind the Avatar’s Mind Read More »
ESSAI is a new yearly event organized under the auspices of the European Association for Artificial Intelligence (EurAI) ESSAI intends to serve as a central hub for PhD students and young researchers working in “all aspects of AI”. The need for such a school emerged in early discussions within CLAIRE and, drawing inspiration from the
ESSAI Summer schools: a longlasting outcome of TAILOR project Read More »
The second cross-cutting Theme Development Workshop (TDW) on “Trusted AI: The Future of Creating Ethical and Responsible AI Systems” was held on 13 September 2023. The TDW was co-organised by all six Networks of AI Excellence (NoE) AI4Media, ELISE, ELSA, euRobin, HumanE-AI-Net, TAILOR together with CLAIRE under the lead of the CSA VISION. The workshop was aimed to develop and identify the most promising and
In July, the ICAPS conference hosted the 10th International Planning Competition (https://ipc2023.github.io/) in Prague. It empirically evaluates state-of-the-art planning systems on a number of benchmark problems. The goals of the IPC are to promote planning research, highlight challenges in the planning community and provide new and interesting problems as benchmarks for future research. The competition
This Data Challenge consists of developing new modules designed to improve the crossword solving performances of the Webcrow 2.0 agent. The set of modules used to evaluate the base system in different human-vs-AI competitions includes experts for various languages (Italian, English, French), implementing clue database search, rule-based solvers, knowledge graph query, web search, candidate list
Automated Crossword Solving Read More »
We are thrilled to announce that some TAILOR scientists will participate in one of the most prestigious conferences in the AI field: The European Conference of Artificial Intelligence (ECAI) 2023 in Krakow. ECAI 2023 will feature a full programme of technical papers, as well as many AI-related events of interest for researchers, students and industry
TAILOR Scientists at ECAI 2023 in Krakow Read More »
Congratulations to Wen Chi Yang, Gavin Rens, Giuseppe Marra and Luc De Raedt on winning the IJCAI 2023 Distinguished Paper Award! The IJCAI Distinguished Paper Awards recognise some of the best papers presented at the conference each year. The winners were selected from among more than 4500 papers by the associate programme committee chairs, the programme and general chairs, and the president of EurAI.
IJCAI2023 Distinguished Paper Award to TAILOR Scientists from KU Leuven Read More »
The EU’s six Networks of AI Excellence Centres (NoEs) are providing a Joint Strategic Research Agenda (SRA). The European Union’s aspirations for AI, Data and Robotics (ADR) that are “made in Europe” demand an ambitious approach to advancing European AI research and development. The EU’s six AI Networks of Excellence (NoEs) – AI4Media, ELISE, ELSA, euROBIN, HUMANE-AI-Net, and
The Joint Strategic Research Agenda (SRA): a collaborative effort for the Future of AI Read More »
Matthias könig PhD at Leiden University Abstract: This project seeks to advance the state of the art in formal neural network verification. Formal neural network verification methods check whether a trained neural network, for example an image classifier, satisfies certain properties or guarantees regarding its behaviour, such as correctness, robustness, or safety, under various inputs
Branislav Pecher PhD at Kempelen Institute of Intelligent Technologies, member of Slovak.AI Abstract: Learning with limited labelled data, such as meta-learning, transfer learning or in-context learning, aims to effectively train a model using only a small amount of labelled samples. However, there is still limited understanding of the required settings or characteristics for these approaches
