DUCK Lab logo DUCK Lab
DUCK
Lab
DataWhat we learn from
UncertaintyWhat we don't know
ConstraintsRules of the world
KnowledgeStructure we trust

We build AI systems that don't just learn from data, but reason over it. Systems that acknowledge what they don't know, respect the rules of the world, and draw on structured knowledge to make better decisions.

DUCK Lab group photo

Four words sit at the heart of everything we do. Data. Uncertainty. Constraints. Knowledge. At the DUCK Lab we build AI systems that don't compromise between being powerful and being safe — a small, tight-knit team at Imperial College London united by the belief that rigor and creativity belong in the same sentence.

Interested in joining the lab? Contact Eleonora at e [DOT] giunchiglia [AT] imperial [DOT] ac [DOT] uk.
🦆 Come for the research, stay for the good company.

Recent news

Jun 2026

Invited talk at CILC 2026

Eleonora will give an invited talk at CILC 2026, the 41st Italian Conference on Computational Logic.

Jun 2026

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 🤗

May 2026

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!

Apr 2026

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.

Mar 2026

Paper accepted at ACL (Findings)

Our paper PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains has been accepted at ACL (Findings) 2026.