STAI CDT PhD student Shahin Honarvar presented the paper, 'Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code' at the 18th IEEE International Conference on Software Testing, Verification and Validation (ICST 2025). We...
In June, STAI CDT PhD student, Richard Willis, will start an exciting new role as a postdoctoral researcher on a highly competitive UK AI Security Institute funded project. Richard will be working on the project, ‘Evaluating the Cooperative Behaviour of Systems of...
In his PhD, STAI CDT student, Lennart Wachowiak is researching how robots can explain their actions to their users. Explainability is a core pillar of safe and trusted AI research as it can help with understanding why things went wrong and whether decisions were made...
STAI CDT student Gabriel Freedman presented a paper at the 11th Workshop on Argument Mining (ArgMining 2024), co-located with the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) last year. The paper, 'Detecting Scientific Fraud Using...
STAI CDT PhD students, Elfia Bezou-Vrakatseli, Chiara Di Bonaventura, Michelle Nwachukwu and Madeleine Waller, led workshops and presented their research at the 11th ACM womEncourage conference in Madrid, Spain. The conference, focused on fostering connections among...
STAI CDT PhD student Dylan Cope presented the paper ‘Mimicry and the Emergence of Cooperative Communication’ at The International Conference for Artificial Life (ALIFE). The conference took place in July in Copenhagen, Denmark. The theme for this years conference was...
STAI CDT student Munkhtulga Battogtokh had a successful trip to EuroVis 2024 in May 2024 where he presented the paper ‘Visual Analytics for Fine-grained Text Classification Models and Datasets’ at the main conference. Munkhtulga was also invited to give a talkat the...
During the STAI CDT Annual Retreat, STAI CDT PhD students had the opportunity to engage in discussions led by their fellow students. Peter Tisnikar and Lennart Wachowiak led a workshop on Large Language Models (LLMs) as decision makers. Peter and Lennart organised the...
STAI CDT PhD students Nathan Schneider Gavenski, Michelle Nwachukwu, Jack Contro and Stefan Roesch, took part in the King’s Festival of Artificial Intelligence with their demonstration, ‘Super Mario Bros: The Turing Quest’. The demonstration was a chance to...
STAI CDT PhD students Elfia Bezou-Vrakatseli and Madeleine Waller edited the recently published fourth volume of The Online Handbook of Argumentation for AI (OHAAI). OHAAI is a curation of selected peer-reviewed papers summarising (ongoing) PhD work on Argumentation...
STAI CDT PhD students Maria Stoica and Gabriel Freedman contributed to the successful Imperial Lates event, which was focused on AI innovations and engaging with the broader community beyond academia. Imperial Lates are fun and social post-work events where visitors...
STAI CDT student Lennart Wachowiak has had the paper 'When Do People Want an Explanation from a Robot?' accepted at this year's upcoming 19th Annual ACM/IEEE International Conference on Human Robot Interaction (HRI 2024). Lennart explains the aim of the research here:...
Anna Gausen is a co-author on a newly published research paper, ‘The Rapid Rise of Generative AI: Assessing Risks to Safety and Security’ by the Centre for Emerging Technologies and Security (CETaS) at the Alan Turing Institute. This CETaS Research Report examines the...
We are excited to announce that STAI CDT students Munkhtulga Battogtokh, Aamal Hussain, Jazon Szabo, Madeleine Waller, Alexander W. Goodall, Francis Rhys Ward and Matt MacDermott have had papers accepted to two of the leading conferences on research in AI: AAAI 2024...
Hana Kopecka has just completed a Digital Humanism Fellowship at The Institute for Human Sciences (IWM). The Institute for Human Sciences (IWM) is an institute of advanced studies in the humanities and social sciences. The fellowship aims to bring eminent...
STAI CDT student Madeleine Waller presented the paper, 'Recommendations for Bias Mitigation Methods: Applicability and Legality' at the Workshop on Fairness and Bias in AI. This workshop was co-located with ECAI 2023 in Kraków, Poland. The paper discusses practical...
STAI CDT student Fabrizio Russo presented the paper 'Causal Discovery and Knowledge Injection for Contestable Neural Networks' at ECAI 2023. Fabrizio explains the paper and its impacts here; "We propose contestable neural networks: neural models whose outputs and...
STAI CDT student Munkhtulga Battogtokh presented the paper “Simple Framework for Interpretable Fine-grained Text Classification” at the 26th European Conference on Artificial Intelligence (ECAI 2023) in Kraków, Poland. Munkhtulga explains the paper here; "As machine...
STAI CDT students Madeleine Waller and Elfia Bezou Vrakatseli gave a workshop at the 10th ACM womENcourage conference in Trondheim, Norway. The conference, focused on fostering connections among women in various STEM fields and supporting their journey in computing,...
STAI CDT student Alexander Goodall (2023 cohort) presented the paper “Approximate Model-based Shielding for Safe Reinforcement Learning” at the 26th European Conference on Artificial Intelligence (ECAI 2023) in Kraków, Poland. Alexander explains the paper here; “We...
STAI CDT students Elfia Bezou Vrakatseli, Benedikt Brückner and Luke Thorburn presented a paper on their framework ‘SHAPE’ at the 20th European Conference on Multi-Agent Systems (EUMAS 2023). The paper is focused on the ethics of influence and provides a practical...
Mackenzie Jorgensen, (2020 STAI CDT PhD cohort) presented the paper 'Not So Fair: The Impact of Presumably Fair Machine Learning Models,' at the 6th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES 23) in Montreal, Canada. Mackenzie...
The UKRI Centre for Doctoral Training (CDT) in Safe and Trusted AI welcomes its fifth cohort. This week, the CDT welcomed a new cohort of 20 students from across King’s and Imperial, all who share a passion for ensuring the safety and trustworthiness of AI. The...
We are excited to announce that Aamal Hussain, Luke Thorburn, Patrick Henriksen and Nathan Gavenski have had papers accepted to three of the leading conferences on research in AI: IJCAI 2023, ICML 2023 and IJCNN 2023. The 32nd International Joint Conference on...
UKRI Centre for Doctoral Training (CDT) in Safe and Trusted AI (STAI) PhD student, Mackenzie Jorgensen (2020 cohort) undertook a six-month internship with the Centre for Data Ethics and Innovation (CDEI). We spoke to Mackenzie about her internship experience and how...
STAI CDT PhD students' work to feature in a new exhibition, Bringing the Human to the Artificial. The exhibition is presented by the King’s Institute for Artificial Intelligence in collaboration with King's Culture, and will showcase cutting-edge research from across...
STAI CDT PhD students Mackenzie Jorgensen (2020 cohort) and Munkhtulga Battogtokh (2020 cohort) recently took part in a KCL Utopia Now! Project with Lambeth Carers Hub. Utopia Now! is a research project based at King’s College London that aims to find out more...
Benedikt Brückner (2021 cohort) presented his paper, ‘A Semidefinite Relaxation based Branch-and-Bound Method for Tight Neural Network Verification’ at the 37 th AAAI Conference on Artificial Intelligence 2023 (AAAI 2023) in Washington DC. Benedikt’s work focuses...
UKRI Safe and Trusted AI PhD student, Patrick Henriksen (2019 cohort) presented his paper, 'Robust Training of Neural Networks against Bias Field Pertubations' at the 37 th AAAI Conference on Artificial Intelligence 2023 (AAAI 2023). The performance of neural networks...
STAI CDT PhD student, Luke Thorburn (2021 cohort) presented a working paper at the inaugural Plurality Research Network Conference, held at UC Berkeley from 13-15 January 2023. Luke, alongside his Harvard collaborator, Aviv Ovadya, have been working on what they call...
We are delighted to announce that Patrick Henriksen (2019 cohort) and Benedikt Brueckner (2021 cohort) have had papers accepted to the 37th AAAI Conference on Artificial Intelligence 2023. The conference takes place in Washington, USA, is one of the top AI...
UKRI Centre for Doctoral Training in Safe and Trusted AI PhD student, Mackenzie Jorgensen (2020 cohort), was the takeover host on the most recent episode of Kings' College London's Careers in Your Ears podcast, ‘Season 8 Episode 2: A career in AI research in academia...
UKRI Safe and Trusted AI PhD student, Anna Gausen (2020 cohort), has had her paper, ‘Using Agent-Based Modelling to Evaluate the Impact of Algorithmic Curation on Social Media’, published in the Association for Computing Machinery’s (ACM) Journal of Data and...
STAI CDT PhD student, Luke Thorburn (2021 cohort), has collaborated with Jonathan Stray (Center for Human-Compatible AI at UC Berkeley) and Pri Bengani (Tow Center for Digital Journalism at Colmbia University) to create the blog, Understanding Recommenders. We spoke...
The UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence is excited to announce that Aamal Hussain (2019 cohort), Francis Rhys Ward (2020 cohort) and Luke Thorburn (2021 cohort) have had papers accepted for this year’s upcoming 22nd...
Mackenzie Jorgensen of the 2020 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence presented her paper, ‘Supposedly Fair Classification Systems and Their Impacts’ at the 2nd Workshop on Adverse Impacts and Collateral Effects of...
Elfia Bezou-Vrakatseli of the 2021 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence presented her paper, ‘Towards an Argument Scheme Classification for Ethical Reasoning’ at the Workshop on Computational Models of Natural...
Jazon Szabo of the 2019 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence contributed his paper, ‘Integrating Quantitative and Qualitative Reasoning for Value Alignment’ to the 19th European Conference on Multi-Agent Systems...
Lennart Wachowiak and Peter Tisnikar of the 2021 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence presented their work on the paper ‘Analysing Eye Gaze Patterns during Confusion and Errors in Human–Agent Collaborations’ at...
Nandi Schoots (2019 cohort), C Henrik R Åslund (2019 cohort), Dylan Cope (2019 cohort), Matt MacDermott (2021 cohort) and Francis Rhys Ward (2020 cohort) of the UKRI Centre for Doctoral Training in Safe and Trusted AI, were the organisers of the Safe and Trustworthy...
Mackenzie Jorgensen, from the 2020 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence, researches the social and ethical implications of AI. In Summer 2021, Vector, the critical journal of the British Science Fiction...
Anna Gausen, of the 2020 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence, presented her research on agent-based modelling and fake news at the Mediate workshop in...
Plans are underway for the Safe and Trusted AI Summer School 2021, to be held online over three days, 12 to 14 July inclusive. Find out more on our Summer School webpage.
What do young people want from the world of the future? How do their hopes and fears intersect with safe and trusted artificial intelligence? To find out, Mackenzie Jorgensen, from the 2020 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial...
Nandi Schoots, of the 2019 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence, presented a paper on the safety properties of inductive logic programming in February 2021. Symbolic approaches to AI are often considered safer...
Jazon Szabo, of the 2019 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted AI, presented his paper on value alignment and norms at the 17th European Conference on Multi-Agent Systems (EUMAS 2020) in September 2020. An increasingly important...
Hana Kopecka, of the 2019 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted AI, has had her paper accepted for publication and presentation at the Workshop on Dialogue, Explanation and Argumentation for Human-Agent Interaction (DEXA...
Congratulations to Patrick Henriksen of the 2019 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted AI, whose paper has been accepted for publication and presentation at the 24th European Conference on Artificial...