Lab news
Invited talk at NESYRE 2026 in Berlin
Eleonora will give an invited talk at NESYRE 2026 — Neuro-symbolic AI, Mathematical Reasoning and Agents — at the Weierstrass Institute in Berlin (14–17 September). The speaker line-up looks amazing! ✨
Tutorial at UAI 2026 in Amsterdam
Mihaela and Eleonora will give a tutorial at UAI 2026 in Amsterdam (17–21 August): Beyond Soft Penalties: Hard Constraints for Neural Networks with Continuous Outputs — how to enforce hard constraints on neural networks with continuous outputs.
Invited talk at TPM 2026 in Amsterdam
Eleonora will give an invited talk at TPM 2026 — the 9th Workshop on Tractable Probabilistic Modeling — in Amsterdam on 21 August, co-located with UAI 2026. Looking forward to meeting this amazing community! ✨
Two papers accepted at NeSy 2026!
🎉 We had two papers accepted at NeSy 2026, the International Conference on Neural-Symbolic Learning and Reasoning! Huge congratulations to Eleni and Jacob, who led these projects as MSc students. Jacob completed his MSc at Imperial, co-supervised by Eleonora and Francesco Belardinelli, while Eleni completed her MSc at Oxford, co-supervised by Eleonora, Giuseppe De Giacomo, and Antonio Di Stasio. ✨
Eleonora on the future of AI panel at Imperial
Eleonora took part in a panel on The future of AI: what’s next and what matters?, organised by the Imperial Policy Forum and chaired by Prof Tom Coates. The discussions were amazing!
Mihaela awarded an IX-WAI Early Career Grant
🎉 Huge congratulations to Mihaela, who has been awarded one of Imperial College London’s IX-WAI Early Career Grants! ✨
Joshua at ICML 2026 in Seoul!
☕ Joshua is at ICML 2026 in Seoul presenting Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models — using MCTS to decide the order in which diffusion language models fill in slots. If you’d like to grab a coffee with him, let us know!
Yani joins as AI for Math Summer Fellow!
🎉 A warm welcome to Yani Zhang, who is joining the DUCK Lab as an AI for Math Summer Fellow! Yani is a final-year PhD student at ETH Zurich working on neural network theory and formal many-valued logic — huge congratulations on winning the fellowship from Renaissance Philanthropy! ✨
Luca delivers AI training across UK Government
Between May and July 2026, Luca delivered AI Fundamentals training to the Cabinet Office (National Security Secretariat), the Department for Science, Innovation and Technology, and the Ministry of Housing, Communities & Local Government, as part of his Research Fellow role at the Imperial Policy Forum.
Lohith joins Capstone as intern!
🎉 Huge congratulations to Lohith, who will be starting an internship at Capstone Investment Advisors — a fantastic match for his research on neurosymbolic AI in financial markets! ✨
Luca featured in the EEE department newsletter
Luca was featured in the Electrical and Electronic Engineering department newsletter at Imperial College London.
Invited talk at CILC 2026
Eleonora gave an invited talk at CILC 2026, the 41st Italian Conference on Computational Logic.
Pythagoras-Prover released!
🚀 We are thrilled to announce the release of Pythagoras-Prover — a compute-efficient family of Lean theorem provers! Strong results at just 4B parameters, powered by Augmented Lean Formalisation. The models are now available on Hugging Face 🤗
Talk at OxBridge Women in CS Conference
On 9 May, Eleonora spoke at the OxBridge Women in CS Conference — a particularly special one for her, as she was herself an OxWoCS member during her PhD!
Luca mentors AI Security Institute Policy Fellow
Since May 2026, Luca has been mentoring Andy Corcoran, Head of National Security Partnering at the AI Security Institute, as part of an ongoing programme on AI for Policy Making — bridging cutting-edge AI research with government practice.
Luca receives Global Promise Endorsement
🎉 Congratulations to Luca, who has been awarded a Global Promise Endorsement by the Royal Academy of Engineering!
Paper accepted at ICML 2026
Our paper Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models has been accepted at ICML 2026.
Paper accepted at ACL (Findings)
Our paper PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains has been accepted at ACL (Findings) 2026.
Luca trains UK civil servants on AI and data governance
In March 2026, Luca delivered AI Fundamentals training to the Cabinet Office (National Security Secretariat) and an AI and Data Governance session to the Department for Science, Innovation and Technology, GOV UK.
Invited talk at the Neurosymbolic AI Workshop
Luca gave an invited talk on Prototypical Neurosymbolic AI at the Neurosymbolic AI Workshop, Imperial College London.
Invited talk at the Neurosymbolic AI Workshop
Lohith gave an invited talk at the Neurosymbolic AI Workshop on Neurosymbolic AI for safe financial portfolio construction.
Joshua joins MBZUAI as visiting student
Joshua is joining MBZUAI as a visiting student, where he will be working on Theorem Proving with LLMs. Please contact him if you want to collaborate!
Luca awarded his PhD in Artificial Intelligence
🎉 Congratulations to Luca, who has been awarded his Italian National PhD in Artificial Intelligence from Sapienza University of Rome, supervised by Prof. Marco Console, on Knowledge Representation!
Survey published in TMLR
Our survey A Survey on Deep Learning Approaches for Tabular Data Generation has been published in Transactions on Machine Learning Research (TMLR).
Luca joins the Imperial Policy Forum as Research Fellow in AI
🎉 Luca has joined the Strategic Engagement Division at Imperial College London as a Research Fellow in AI with the Imperial Policy Forum, delivering research and expert-led training on AI directly relevant to government policy.
Luca begins supervising Master's thesis on neurosymbolic learning
From November 2025 to July 2026, Luca is supervising Lolézio Viora Marquet’s Master’s thesis, Prototype-Augmented Neurosymbolic Learning under Multi-Modal Data Distributions.
Frontiers in AI invited talk at ECAI 2025
Eleonora gave one of the Frontiers in AI invited talks at ECAI 2025.
Paper accepted at NeurIPS 2025
Our paper Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI has been accepted at NeurIPS 2025.
AI for Math Fund
Eleonora has been awarded an AI for Math grant. Read more here
Paper published at ECAI 2025
Eleonora’s paper A Posteriori Verification or a Priori Design? Navigating Requirements-Driven Deep Learning has been published at ECAI 2025.