Associate Professor (@uclcs, @ai_ucl) leading the Ωmega research group (@omega_ucl) | research: AI, NLP, health | dad | ☮

London, UK
In our paper, the final version of which was published this week in @NatureComms, we study the clinical task of switching patients from intravenous to oral antibiotic treatment. Paper: nature.com/articles/s41467-0… Code: github.com/SAFEHR-data/ivos-… 1/
1
2
5
325
The work was led by @magnusaross and was co-authored by an amazing team of clinical and machine learning experts (Nel Swanepoel, Akish Luintel, Emma McGuire, Ingemar Cox, Steve Harris). 6/
1
20
The research was supported by @AMR_DHH and the RADIX (Real-time Antimicrobial Digital Intervention eXchange) programme at UCLH. cc: @uclcs, @ai_ucl 7/
25
Excited to share our (w/ Minoo Kim and @g_drayson) new preprint "Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation". Paper: arxiv.org/abs/2610.00348 Code: github.com/LocaiLabs/NEEDLE Models: huggingface.co/collections/l… /1
1
1
5
166
(2) The excellence of our Machine Learning MSc students at @uclcs. The work was led by Minoo Kim and was based on his MSc Project. Congratulations Minoo! /3
1
48
(3) The excellence and research readiness of our industrial partners. @locai_labs, and George Drayson in particular, provided a rigorous, research-led supervision to this project. cc: @ai_ucl
32
Vasileios Lampos retweeted
People are increasingly worried about backdoors in LLMs… so we developed a method to remove them. New paper: Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation Congratulations to Minoo Kim for leading this work and @lampos
1
3
5
101
Delighted to share that our paper "From Jumps to Signatures: a Generative Method for Temporal Point Processes" has been accepted at #NeurIPS2026. Preprint: arxiv.org/abs/2607.06652 Code: github.com/Code-Cornelius/si… 1/
1
2
4
173
Huge congratulations to my amazing PhD student, Niels D. Cariou Kotlarek, for leading this! In this work, we address a fundamental gap in generative TPPs: the lack of global sequence-level loss functions and mathematically justified distributional discrepancy measures. 2/
1
2
3
309
We introduce sigTPP, a model that replaces traditional per-event training with a global signature-based loss. Our camera-ready version will include more expansive results. cc: @ai_ucl, @uclcs 3/
1
57
Ed Sheeran is not Eric Clapton.
102
Mission accomplished. 🤮
It has been an honour and a privilege to represent Holborn and St Pancras for the last 11 years. My statement.
122
Artificial Intelligence is a critical national infrastructure. Government and industry increasingly depend on foundation models whose security, transparency, and reliability are essential. /1
3
6
15
3,030