Posts

Recognizing early-career researchers who have made a significant impact at the University, for breakthrough research in Agentic AI Safety and Security.

Our Agent Trust Simulation project received the Outstanding Paper Award at the 1st Workshop on LLM Agents for Social Simulation (LASS) at CIKM 2025.

Awarded the Coefficient Giving Grant (~$260,000) to investigate transferable adversarial inputs that can induce malicious agent behaviour

Awarded the Toyota Motor Europe Grant (~$330,000) in 2025 to work on agentic and multi-agent safety.

I received the Excellence Award from the Engineering Science Department at Oxford University for outstanding performance throughout 2024/2025.

I received the Systemic AI Safety Grant (~$250,000) for our work on Safe OS Agents

I received the Google Gemma 2 Academic Program GCP Credit Award ($10,000) for my project on certifying the output of Large Language Models.

The award is presented to our paper “Paper: When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations” in the NeurIPS23 Workshop I Cant Believe Its Not Better (ICBINB): Failure Modes in the Age of Foundation Models.

Unfortunately, I did not attend NeurIPS 23 this year as I was ill (luckily, my student Aleksandar Petrov was there to present our paper). However, to my surprise, he sent me this image where I was selected as a notable Area Chair.

The award is presented to our paper “Provably Correct Physics-Informed Neural Networks” in the Workshop on Formal Verification of Machine Learning (WFVML 2023) in ICML23. Congrats to the my student Francisco Eiras.