I am a Postdoctoral Researcher at the University of Copenhagen, working with the LAMP group and affiliated with CoAStaL NLP and the Pioneer Center for AI. My research focuses on the development, evaluation, and applications of vision-and-language models, with an interest in their safety, robustness, and responsible deployment.
I completed my Ph.D. in Natural Language Processing at the University of Sheffield (UK), supervised by Professor Nikos Aletras, where I worked on computational social science, political communication, and multimodal modeling. Previously, I was a Research Associate at SheffieldNLP and an Applied Scientist Intern at Amazon Alexa Shopping.
I am broadly interested in NLP, multimodal learning, and safe AI systems. Outside of research, I enjoy pilates and learning new languages. I am an active member of the LatinX in AI community and an organizer of SomosNLP, an Ibero-American NLP community.
📧 Email: davi@di.ku.dk
[Blog] [Publications] [Google Scholar]
News
- Mar 2026
- I joined the PI Program AI & Society and I will present our work MuSeD: A Multimodal Spanish Dataset for Sexism Detection in Social Media Videos at the inaugural event in Copenhagen!
- Our paper Movie Facts and Fibs (MF): A Benchmark for Long Movie Understanding has been accepted at ICLR 2026 Workshop on Multimodal Intelligence.
- Feb 2026 Our new pre-print is out! Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos
- Dec 2025
- I will give a talk on Visual Language Models and its applications to social good at IIMAS-UNAM and ITAM Universities in Mexico City.
- I will be attending NeurIPS in Mexico city! I am co-organizing The SomosNLP Social and I will present our recent work, ImageChain, at the LatinX in AI Workshop.
- Nov 2025
- 1 paper accepted to appear in WACV! ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models
- Our paper Evaluation Reporting in AI Model Releases should be Standardized was accepted in EurIPS 2025 Workshop on The Science of Benchmarking and Evaluating AI.