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 UCL Centre for Artificial Intelligence and the Intelligent Systems Group.

PhD Studentships Available

We are advertising two PhD projects in the area of AI Cybersecurity as part of the EPSRC Centre for Doctoral Training in Cyber-Physical Risk. You can find the project proposals here. Closing date (extended): 25 April 2025. Please feel free to contact Prof. Mirco Musolesi if you are interested in discussing more.

What’s New

• April 2025 Liza Karmannaya will present her work “Moral Alignment for LLM Agents” at 13th International Conference on Learning Representations (ICLR 2025). You can download the paper here.

• April 2025 Our paper “Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis” has been accepted for publication in the Blue Sky Track of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025). You can download the paper here.

• April 2025 Congratulations to Giorgio Franceschelli for successfully defending his PhD thesis!

• March 2025 Our paper “Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systems” has been accepted in the Journal of Autonomous Agents and Multi-Agent Systems (JAAMAS). You can download the paper here.

• February 2025 Our paper “Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systems” has been accepted in the Journal of Autonomous Agents and Multi-Agent Systems (JAAMAS). The camera ready of the article will be available soon. In the meantime, you can download the preprint here.

• February 2025 New preprint: “DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation”. You can download the paper here.

• February 2025 New preprint: “Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation”. You can download the paper here.

• January 2025 Our paper “Moral Alignment for LLM Agents” has been accepted for publication at the 13th International Conference on Learning Representations (ICLR 2025). The camera ready version will be available soon. In the meantime, you can find the preprint here.

• January 2025 Our paper “Partial Information Decomposition for Data Interpretability and Feature Selection” has been accepted at the 28th International Conference on Artificial Intelligence and Statistics (AISTAT 2025). The camera ready version will be available soon. In the meantime, you can find the preprint here.

• January 2025 Our paper “A Cost-aware Adaptive Bike Repositioning Agent using Deep Reinforcement Learning” has been accepted in IEEE Transactions on Intelligent Transportation Systems. The camera ready version will appear soon. In the meantime, you can download the preprint of the paper here.

• November 2024 Our paper “Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies” has been accepted at the 3rd Learning on Graph Conference (LoG 2024). The preprint of the paper can be found here.

• November 2024 Our paper “Feature Selection for Network Intrusion Detection” has been accepted for publication in the Research Track of the 31st ACM Conference on Knowledge Discovery and Data Mining (ACM SIGKDD 2025). The camera ready version will be available soon. In the meantime, you can find the preprint here.

• November 2024 New preprint: “Mutual Information Preserving Neural Network Pruning”. You can download the paper here.

• November 2024 Our paper “On the Creativity of Large Language Models” has been accepted for publication in AI&Society. The camera ready version of the paper will be ready soon. In the meantime, you can find a preprint of the article here.

Previous news items can be found here.

Last updated: 25 April 2025.