Machine Intelligence Lab

Welcome to the website of the Machine Intelligence Lab at the Department of Computer Science at University College London (UCL). We are part of the the UCL-CS Autonomous Systems Group.

What’s New

  • New preprint: “Moral Alignment for LLM Agents”. You can download the paper here.

  • Our paper “InterruptMe: Designing Intelligent Prompting Mechanisms for Pervasive Applications” has been awarded a Best Paper Runner-up Award in the 10-year Impact Awards category at ACM UbiComp 2024. You can find our UbiComp 2014 paper here. This work was led by Veljko Pejovic, a postdoc in the lab at that time and now Associate Professor at the University of Ljubljana.

  • Our paper “Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery” has been accepted of publication in the Proceedings of the Royal Society A. The paper will be appear soon. You can find the arXiv preprint here.

  • We won the Best Paper Award for the paper “MarcoPolo: A Zero-Permission Attack for Location Type Inference from the Magnetic Field Using Mobile Devices” at CANS 2024. You can download the paper here.

  • New preprint: “Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies”. You can download the paper here.

  • Our paper “Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective” has been accepted for publication in Transactions on Machine Learning Research (TMLR). The paper will appear soon, in the meantime you can download the preprint here.

  • Our manifesto paper “Ecological Brain: Reframing the Study of Human Behaviour and Cognition” co-authored with the students of the first cohorts of our Leverhulme Doctoral Training Programme for the Ecological Study of the Brain has been accepted for publication in Royal Society Society Open Science. The preprint of the paper is available here.

  • New preprint: “Flourishing Diversity in AI”. You can download the paper here.

  • Our paper “Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents” has been accepted in the Proceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2024). You can find the preprint of the paper here.

  • Our paper “Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law” will be presented at the 2nd Internation Workshop on Generative AI and Law (GenLaw 2024), colocated with the 41st International Conference on Machine Learning (ICML 2024), as spotlight presentation. You can download the paper here.

  • Alessandro Staffolani successfully defended his PhD on 25 June 2024. Well done Alessandro!

  • New preprint: “Partial Information Decomposition for Data Interpretability and Feature Selection”. You can download the paper here.

  • Our paper “(Ir)rationality and Cognitive Biases in Large Language Models” is now out in Royal Society Open Science. You can download the paper here.

  • Our paper “Game-theoretic Agent-based Modelling of Micro-level Conflict: Evidence from the ISIS-Kurdish War” is now out in PLOS ONE. You can download the paper here.

  • New preprint: “Large Language Models are Effective Priors for Causal Graph Discovery”. You can download the paper here.

  • Our paper “Creative Beam Search: LLM-as-a-Judge for Improving Response Generation has been accepted for publication in the proceedings of the 15th International Conference on Computational Creativity (ICCC 2024). You can download the paper here.

  • Our paper “Trust-based Consensus in Multi-Agent Reinforcement Learning Systems” has been accepted at the 1st Reinforcement Learning Conference (RLC 2024). The camera ready version will be available soon. In the meantime, you can download the preprint here.

Previous news items can be found here.



Last updated: 21 October 2024.