I’m a Postdoctoral Researcher at the University of Copenhagen, working on large multimodal models for video and language understanding. My current research focuses on model development, evaluation, and real-world applications of vision-and-language systems. I completed my Ph.D. in Natural Language Processing at the University of Sheffield (UK), supervised by Professor Nikos Aletras, with research spanning computational social science, political communication, and multimodal modeling. I also hold an MSc in Computer Science from Sheffield and a BSc in Computer Engineering from ITAM (Mexico City). Previously, I worked as a Research Associate in the SheffieldNLP group and as an Applied Scientist Intern at Amazon Alexa Shopping, where I focused on generative language models.
My research interests lie at the intersection of NLP, vision-and-language modeling, and socially impactful AI.
Outside of research, I enjoy yoga and pilates, and I’m passionate about mentoring students—especially from Latin America and other underrepresented communities in AI.
📧 Email: davi@di.ku.dk
[Blog] [Publications] [Google Scholar]
News
- Jul 2025 Attending ACL 2025! Co-organizing the Affinity Group Event—SomosNLP: The Iberoamerican NLP Community. See you in Vienna!
- Jun 2025 Co-organizing the Copenhagen NLP Symposium. Join us for a day of talks, a poster session and great discussions! Organized in collaboration by researchers at ITU, University of Copenhagen, and Aalborg University in Copenhagen.
- May 2025 Giving a talk at SomosNLP Hackathon on sequential image-to-text reasoning with multimodal large language models.
- Apr 2025 Happy to share our most recent work! MuSeD: A Multimodal Spanish Dataset for Sexism Detection in Social Media Videos This project is the result of a great collaboration with Laura de Grazia from Universitat de Barcelona (UB) where I had the pleasure of serving as senior co-supervisor.
- Mar 2025
- Excited to share our new work led by Antonia Karamolegkou! Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users.
- I am also giving a talk at the Research Connections session from Cohere Labs where I shared my work on multimodal learning and video content analysis.
- Feb 2025 Our latest paper is now available on arXiv! ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models
- Jan 2025 Teaching NLP topics at the University of Copenhagen. Deep Learning Course for graduate students.