I am a computer scientist whose research sits at the intersection of AI systems and human behaviour. I study how cognitive biases, particularly those rooted in physical appearance, shape human judgment and propagate into AI, spanning multimodal large language models, text-to-image generation, and computer vision. What distinguishes my work is a commitment to large-scale mixed methods: I combine computational AI evaluation with controlled behavioural experimentation to ask questions neither approach can answer alone.

My PhD at ELLIS Alicante, advised by Nuria Oliver, Bruno Lepri, and Miguel Ángel Lozano, centred on the attractiveness halo effect, asking whether the biases that lead humans to attribute positive qualities to attractive people also shape how AI systems see, generate, and evaluate faces. To answer this, I built evaluation pipelines for multimodal LLMs, probed text-to-image generators for lookism, and ran large-scale crowdsourced experiments (N = 2,700+), producing evidence grounded in both systems and people.

Previously, I was a visiting researcher at Fondazione Bruno Kessler (Trento), a research intern at the Dynamic Decision Making Lab at Carnegie Mellon University, a research assistant at the Machine Perception Lab at IIIT Bangalore, and a visiting scientist at the Vision and Perception Science Group at Ulm University.