Multimodal Fact-Checking
Verifying claims by jointly reasoning over text and visual evidence.
I am a PhD student in the UKP lab at the Institute for Computer Science, Artificial Intelligence and Technology (INSAIT), where I am working on multimodal fact-checking under the supervision of Prof. Iryna Gurevych.
Previously, I served as a Research Assistant at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), focusing on parameter-efficient fine-tuning techniques for Large Language Models (LLMs) under the guidance of Prof. Thamar Solorio. I completed my MSc in Computer Science at the Universidad Nacional Autónoma de México (UNAM), advised by Dr Gemma Bel-Enguix.
In my free time, I enjoy snowboarding 🏂, mountain biking 🚵, and playing football ⚽. I’m a fan of Pumas UNAM
, Diablos Rojos del México
, and CSKA Sofia .
Verifying claims by jointly reasoning over text and visual evidence.
Adapting large language models to new tasks under limited compute and data.
Broader interests in NLP, with a focus on low-resource and multilingual settings.
Studies how adversarial instructions can manipulate LLM-generated charts to misrepresent the underlying data.
A lightweight fine-tuning approach that achieves strong cross-lingual generalization in encoder-only models, without the compute costs of large decoder-only LLMs.
A culturally-diverse multilingual Visual Question Answering benchmark, designed to evaluate multimodal models on culturally grounded visual understanding.